CN110764897A

CN110764897A - Graphics system with additional context

Info

Publication number: CN110764897A
Application number: CN201910813813.5A
Authority: CN
Inventors: B.英斯科; C.萨克蒂韦尔; D.温巴尔; E.奥尔德-艾哈迈德-瓦尔; H.拉贝; A.桑原; R.文卡塔拉曼; M.拉马多斯; P.瑟蒂; J.雷; A.阿普; A.沙; A.卡尔拉
Original assignee: Intel Corp
Current assignee: Intel Corp
Priority date: 2017-04-17
Filing date: 2018-04-17
Publication date: 2020-02-07
Anticipated expiration: 2038-04-17
Also published as: TW201946031A; TW201926246A; EP3611621A1; US20190180494A1; TWI783972B; CN110634097A; CN108734633A; US20180300932A1; TWI787494B; US11217004B2; US20220270317A1; US11954783B2; EP3392769A1; US20180300934A1; TWI706380B; TW201839719A; CN110634097B; EP3657333A1; CN117971461A; US10467796B2

Abstract

An embodiment of an electronic processing system may include an application processor, a persistent storage medium communicatively coupled to the application processor, and a graphics subsystem communicatively coupled to the application processor. The graphics subsystem may include a first graphics engine to process a graphics workload and a second graphics engine to offload at least a portion of the graphics workload from the first graphics engine. The second graphics engine may include a low precision computing engine. The system may further include a wearable display equipped with a second graphics engine. Other embodiments are described and claimed.

Description

Graphics system with additional context

Technical Field

Embodiments relate generally to data processing and to graphics processing via a graphics processing unit. More particularly, embodiments relate to graphics systems with additional context.

Background

Current parallel graphics data processing includes systems and methods developed to perform specific operations on graphics data, such as, for example, linear interpolation, tessellation, rasterization, texture mapping, depth testing, and so forth. Traditionally, graphics processors use fixed function computing units to process graphics data; more recently, however, some graphics processors have been made programmable to enable such processors to support a wide variety of operations for processing vertex and fragment data. Various graphics operations may be divided into workloads.

Drawings

The various advantages of the embodiments will become apparent to those skilled in the art by reading the following specification and appended claims, and by referencing the following drawings, in which:

FIG. 1 is a block diagram illustrating a computer system configured to implement one or more aspects of the embodiments described herein;

2A-2D illustrate parallel processor components according to embodiments;

3A-3B are block diagrams of a graphics multiprocessor according to an embodiment;

4A-4F illustrate exemplary architectures in which multiple GPUs are communicatively coupled to multiple multicore processors;

FIG. 5 illustrates a graphics processing pipeline according to an embodiment;

fig. 6 is a block diagram of an example of an electronic processing system according to an embodiment;

fig. 7 is a block diagram of an example of a graphics device according to an embodiment;

8A-8C are flow diagrams of examples of methods of processing a graphics workload according to embodiments;

fig. 9 is a block diagram of an example of a graphics system according to an embodiment;

FIG. 10 is a block diagram of another example of a graphics system according to an embodiment;

fig. 11 is an illustration of an example of a Head Mounted Display (HMD) system according to an embodiment;

fig. 12 is a block diagram of an example of functional components included in the HMD system of fig. 11, in accordance with an embodiment;

FIG. 13 is a block diagram of an example of a general purpose processing cluster included in a parallel processing unit according to an embodiment;

FIG. 14 is a conceptual illustration of an example of a graphics processing pipeline that may be implemented within a parallel processing unit according to an embodiment;

FIG. 15 is a block diagram of an example of a streaming multiprocessor according to an embodiment;

16-18 are block diagrams of examples of an overview of a data processing system according to an embodiment;

fig. 19 is a block diagram of an example of a graphics processing engine according to an embodiment;

20-22 are block diagrams of examples of execution units according to embodiments;

FIG. 23 is a block diagram of an example of a graphics pipeline, according to an embodiment;

24A-24B are block diagrams of examples of graphics pipeline programming according to embodiments;

FIG. 25 is a block diagram of an example of a graphics software architecture, according to an embodiment;

fig. 26 is a block diagram of an example of an Intellectual Property (IP) core development system, according to an embodiment;

fig. 27 is a block diagram of an example of a system-on-chip integrated circuit according to an embodiment.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that the present invention may be practiced without one or more of these specific details. In other instances, well-known features have not been described in order to avoid obscuring the present invention.

Overview of the System

FIG. 1 is a block diagram illustrating a computing system 100 configured to implement one or more aspects of the embodiments described herein. Computing system 100 includes a processing subsystem 101, the processing subsystem 101 having one or more processors 102 and a system memory 104, the one or more processors 102 and the system memory 104 communicating via an interconnection path that may include a memory hub 105. The memory hub 105 may be a separate component within a chipset component or may be integrated within the one or more processors 102. The memory hub 105 is coupled with the I/O subsystem 111 via a communication link 106. The I/O subsystem 111 includes an I/O hub 107, which I/O hub 107 may enable the computing system 100 to receive input from one or more input devices 108. Additionally, the I/O hub 107 may enable a display controller, which may be included in the one or more processors 102, to provide output to one or more display devices 110A. In one embodiment, the one or more display devices 110A coupled with the I/O hub 107 may include local, internal, or embedded display devices.

In one embodiment, the processing subsystem 101 includes one or more parallel processors 112, the parallel processors 112 coupled to the memory hub 105 via a bus or other communication link 113. The communication link 113 may be one of any number of standards-based communication link technologies or protocols, such as but not limited to a PCI express bus, or may be a vendor-specific communication interface or communication structure. In one embodiment, the one or more parallel processors 112 form a computationally intensive parallel or vector processing system that includes a large number of processing cores and/or processing clusters (such as integrated many-core (MIC) processors). In one embodiment, the one or more parallel processors 112 form a graphics processing subsystem that can output pixels to one of the one or more display devices 110A coupled via the I/O hub 107. The one or more parallel processors 112 may also include a display controller and display interface (not shown) to enable direct connection to one or more display devices 110B.

Within I/O subsystem 111, system storage unit 114 may be connected to I/O hub 107 to provide a storage mechanism for computing system 100. The I/O switch 116 may be used to provide an interface mechanism to enable connections between the I/O hub 107 and other components, such as a network adapter 118 and/or a wireless network adapter 119 that may be integrated into a platform, as well as various other devices that may be added via one or more plug-in devices 120. The network adapter 118 may be an ethernet adapter or another wired network adapter. The wireless network adapter 119 may include one or more of the following: Wi-Fi, Bluetooth, Near Field Communication (NFC), or other network device that includes one or more wireless radios.

Computing system 100 may include other components not explicitly shown, including USB or other port connections, optical storage drives, video capture devices, and the like, which may also be connected to I/O hub 107. The communication paths interconnecting the various components in fig. 1 may be implemented using any suitable protocol, such as a PCI (peripheral component interconnect) based protocol (e.g., a PCI express bus) or any other bus or point-to-point communication interface and/or protocol (such as an NV-Link express interconnect, or interconnect protocol known in the art).

In one embodiment, the one or more parallel processors 112 incorporate circuitry optimized for graphics and video processing (including, for example, video output circuitry) and constitute a Graphics Processing Unit (GPU). In another embodiment, the one or more parallel processors 112 incorporate circuitry optimized for general purpose processing while maintaining the underlying computing architecture described in more detail herein. In yet another embodiment, components of computing system 100 may be integrated together with one or more other system elements on a single integrated circuit. For example, the one or more parallel processors 112, memory hub 105, processors 102, and I/O hub 107 may be integrated into a system-on-chip (SoC) integrated circuit. Alternatively, components of computing system 100 may be integrated into a single package to form a system-in-package (SIP) configuration. In one embodiment, at least portions of the components of computing system 100 may be integrated into a multi-chip module (MCM) that may be interconnected into a modular computing system along with other multi-chip modules.

It will be appreciated that the computing system 100 shown herein is illustrative and that variations and modifications are possible. The connection topology may be modified as desired, including the number and arrangement of bridges, the number of processor(s) 102, and the number of parallel processor(s) 112. For example, in some embodiments, system memory 104 is connected to processor(s) 102 directly rather than through a bridge, while other devices communicate with processor(s) 102 and system memory 104 via memory hub 105. In other alternative topologies, parallel processor(s) 112 are connected to I/O hub 107 or directly to one of the one or more processors 102 rather than to memory hub 105. In other embodiments, the I/O hub 107 and the memory hub 105 may be integrated into a single chip. Some embodiments may include two or more sets of processors 102 attached via multiple sockets, which may be coupled with two or more instances of parallel processor(s) 112.

Some of the specific components shown herein are optional and may not be included in all implementations of computing system 100. For example, any number of plug-in cards or peripherals may be supported, or some components may be eliminated. Further, some architectures may use different terminology for components similar to those shown in fig. 1. For example, in some architectures memory hub 105 may be referred to as a north bridge and I/O hub 107 may be referred to as a south bridge.

FIG. 2A illustrates a parallel processor 200 according to an embodiment. Various components of parallel processor 200 may be implemented using one or more integrated circuit devices, such as a programmable processor, an Application Specific Integrated Circuit (ASIC), or a Field Programmable Gate Array (FPGA). According to an embodiment, the parallel processor 200 shown is a variation of one or more of the parallel processors 112 shown in FIG. 1.

In one embodiment, parallel processor 200 includes parallel processing unit 202. The parallel processing unit includes an I/O unit 204, the I/O unit 204 enabling communication with other devices, including other instances of the parallel processing unit 202. The I/O unit 204 may be directly connected to other devices. In one embodiment, the I/O unit 204 interfaces with other devices via the use of a hub or switch interface, such as the memory hub 105. The connection between the memory hub 105 and the I/O unit 204 forms a communication link 113. Within parallel processing unit 202, I/O unit 204 is connected to host interface 206 and memory crossbar 216, where host interface 206 receives commands for performing processing operations and memory crossbar 216 receives commands for performing memory operations.

When the host interface 206 receives the command buffers via the I/O unit 204, the host interface 206 may direct the work operations for executing those commands to the front end 208. In one embodiment, the front end 208 is coupled to a scheduler 210, the scheduler 210 configured to distribute commands or other work items to a processing cluster array 212. In one embodiment, scheduler 210 ensures that processing cluster array 212 is properly configured and in a valid state before tasks are distributed to the processing clusters of processing cluster array 212. In one embodiment, scheduler 210 is implemented via firmware logic executing on a microcontroller. The microcontroller-implemented scheduler 210 may be configured to perform complex scheduling and work distribution operations at both coarse and fine granularity, enabling context switching and fast preemption (rapiddpreemption) of threads executing on the processing array 212. In one embodiment, the host software may verify that a workload is scheduled on processing array 212 via one of a plurality of graphics processing doorbells (graphics processing doorbells). The workload may then be automatically distributed across processing array 212 by scheduler 210 logic within the scheduler microcontroller.

Processing cluster array 212 may include up to "N" processing clusters (e.g., cluster 214A, cluster 214B, up to cluster 214N). Each cluster 214A-214N of processing cluster array 212 may execute a large number of concurrent threads. Scheduler 210 may use various scheduling and/or work distribution algorithms to assign work to clusters 214A-214N of processing cluster array 212, which may vary depending on the workload generated for each type of program or computation. Scheduling may be handled dynamically by scheduler 210 or may be assisted in part by compiler logic during compilation of program logic configured for execution by processing cluster array 212. In one embodiment, different clusters 214A-214N of processing cluster array 212 may be allocated for processing different types of programs, or for performing different types of computations.

Processing cluster array 212 may be configured to perform various types of parallel processing operations. In one embodiment, processing cluster array 212 is configured to perform general purpose parallel computing operations. For example, the processing cluster array 212 may include logic to perform processing tasks including filtering video and/or audio data, performing modeling operations (including physical operations), and performing data transformations.

In one embodiment, processing cluster array 212 is configured to perform parallel graphics processing operations. In embodiments in which parallel processor 200 is configured to perform graphics processing operations, processing cluster array 212 may include additional logic to support the performance of such graphics processing operations, including but not limited to texture sampling logic to perform texture operations, as well as tessellation logic and other vertex processing logic. Additionally, processing cluster array 212 may be configured to execute graphics processing-related shader programs, such as, but not limited to, vertex shaders, tessellation shaders, geometry shaders, and pixel shaders. Parallel processing unit 202 may transfer data from system memory for processing via I/O unit 204. During processing, the transferred data may be stored to an on-chip memory (e.g., parallel processor memory 222) during processing and then written back to system memory.

In one embodiment, when the parallel processing unit 202 is used to perform graphics processing, the scheduler 210 may be configured to divide the processing workload into approximately equal sized tasks to better enable distribution of graphics processing operations to the multiple clusters 214A-214N in the processing cluster array 212. In some embodiments, portions of processing cluster array 212 may be configured to perform different types of processing. For example, a first portion may be configured to perform vertex shading and topology generation, a second portion may be configured to perform tessellation and geometric shading, and a third portion may be configured to perform pixel shading or other screen space operations to produce a rendered image for display. Intermediate data generated by one or more of the clusters 214A-214N may be stored in a buffer to allow the intermediate data to be transferred between the clusters 214A-214N for further processing.

During operation, processing cluster array 212 may receive processing tasks to be executed via scheduler 210, which receives commands defining the processing tasks from front end 208. For graphics processing operations, a processing task may include command and status parameters that define how data is to be processed (e.g., what program is to be executed) and an index of data to be processed (e.g., surface (patch) data, primitive data, vertex data, and/or pixel data). Scheduler 210 may be configured to extract the index corresponding to the task or may receive the index from front end 208. The front end 208 may be configured to ensure that the processing cluster array 212 is configured to a valid state prior to initiating a workload specified by an incoming command buffer (e.g., a batch buffer, a push buffer, etc.).

Each of the one or more instances of parallel processing unit 202 may be coupled with parallel processor memory 222. The parallel processor memory 222 may be accessed via a memory crossbar 216, and the memory crossbar 216 may receive memory requests from the processing cluster array 212 and the I/O unit 204. Memory crossbar 216 may access parallel processor memory 222 via memory interface 218. Memory interface 218 may include a plurality of partition units (e.g., partition unit 220A, partition unit 220B, up to partition unit 220N), which may each be coupled to a portion (e.g., a memory unit) of parallel processor memory 222. In one implementation, the number of partition units 220A-220N is configured to equal the number of memory units, such that a first partition unit 220A has a corresponding first memory unit 224A, a second partition unit 220B has a corresponding memory unit 224B, and an Nth partition unit 220N has a corresponding Nth memory unit 224N. In other embodiments, the number of partition units 220A-220N may not equal the number of memory devices.

In various embodiments, memory units 224A-224N may comprise various types of memory devices, including Dynamic Random Access Memory (DRAM) or graphics random access memory, such as Synchronous Graphics Random Access Memory (SGRAM), including Graphics Double Data Rate (GDDR) memory. In one embodiment, memory units 224A-224N may also comprise 3D stacked memory, including but not limited to High Bandwidth Memory (HBM). Those skilled in the art will recognize that the particular implementation of memory cells 224A-224N may vary and may be selected from one of a variety of conventional designs. Render targets, such as frame buffers or texture maps, may be stored across the memory units 224A-224N, allowing the partition units 220A-220N to write portions of each render target in parallel to efficiently use the available bandwidth of the parallel processor memory 222. In some embodiments, local instances of the parallel processor memory 222 may be eliminated in favor of a unified memory design that utilizes system memory in conjunction with local cache memory.

In one embodiment, any of the clusters 214A-214N of the processing cluster array 212 may process data to be written to any of the memory units 224A-224N within the parallel processor memory 222. The memory crossbar 216 may be configured to transfer the output of each cluster 214A-214N to any partition unit 220A-220N or another cluster 214A-214N, which may perform additional processing operations on the output. Each cluster 214A-214N may communicate with a memory interface 218 through a memory crossbar 216 to read from or write to various external memory devices. In one embodiment, memory crossbar 216 has a connection to memory interface 218 to communicate with I/O unit 204 and a connection to a local instance of parallel processor memory 222, thereby enabling processing units within different processing clusters 214A-214N to communicate with system memory or other memory not local to parallel processing unit 202. In one embodiment, the memory crossbar 216 may use virtual channels to separate traffic flows between the clusters 214A-214N and the partition units 220A-220N.

Although a single instance of parallel processing unit 202 is shown within parallel processor 200, any number of instances of parallel processing unit 202 may be included. For example, multiple instances of parallel processing unit 202 may be provided on a single plug-in card, or multiple plug-in cards may be interconnected. Different instances of parallel processing unit 202 may be configured to interoperate even if the different instances have different numbers of processing cores, different amounts of local parallel processor memory, and/or other configuration differences. For example and in one embodiment, some instances of parallel processing unit 202 may include a higher precision floating point unit relative to other instances. A system incorporating one or more instances of parallel processing unit 202 or parallel processor 200 may be implemented in a variety of configurations and form factors (form factors), including but not limited to desktop, laptop, or handheld personal computers, servers, workstations, game consoles, and/or embedded systems.

Fig. 2B is a block diagram of a partition unit 220 according to an embodiment. In one embodiment, partition unit 220 is an example of one of partition units 220A-220N of FIG. 2A. As shown, partition unit 220 includes L2 cache 221, frame buffer interface 225, and ROP 226 (raster operations unit). L2 cache 221 is a read/write cache configured to perform load and store operations received from memory crossbar 216 and ROP 226. Read misses (readmiss) and urgent writeback requests are output by L2 cache 221 to frame buffer interface 225 for processing. Updates may also be sent to the frame buffer for processing via frame buffer interface 225. In one embodiment, frame buffer interface 225 interfaces with one of the memory units in parallel processor memory, such as memory units 224A-224N of FIG. 2 (e.g., within parallel processor memory 222).

In graphics applications, ROP 226 is a processing unit that performs raster operations such as stencil printing (STENCIL), z-testing, blending, and the like, then ROP 226 outputs processed graphics data that is stored in graphics memory.

In some embodiments, ROP 226 is included within each processing cluster (e.g., clusters 214A-214N of FIG. 2) rather than partition unit 220. In such embodiments, read and write requests for pixel data are communicated through memory crossbar 216 instead of pixel fragment data. The processed graphics data may be displayed on a display device (such as one of the one or more display devices 110 of fig. 1), routed for further processing by processor(s) 102, or routed for further processing by one of the processing entities within parallel processor 200 of fig. 2A.

FIG. 2C is a block diagram of processing cluster 214 within a parallel processing unit, according to an embodiment. In one embodiment, the processing cluster is an instance of one of the processing clusters 214A-214N of FIG. 2. Processing cluster 214 may be configured to execute a number of threads in parallel, where the term "thread" refers to an instance of a particular program executing on a particular set of input data. In some embodiments, Single Instruction Multiple Data (SIMD) instruction issue techniques are used to support parallel execution of a large number of threads without providing multiple independent instruction units. In other embodiments, Single Instruction Multiple Threading (SIMT) techniques are used to support parallel execution of a large number of generally simultaneous threads using a common instruction unit configured to issue instructions to a set of processing engines within each of the processing clusters. Unlike the SIMD execution regime, in which all processing engines typically execute the same instructions, SIMT execution allows different threads to more easily follow divergent execution paths through a given thread program. Those skilled in the art will appreciate that the SIMD processing regime represents a functional subset of the SIMT processing regime.

The operation of the processing clusters 214 may be controlled via a pipeline manager 232 that distributes processing tasks to SIMT parallel processors. Pipeline manager 232 receives instructions from scheduler 210 of FIG. 2 and manages the execution of those instructions via graphics multiprocessor 234 and/or texture unit 236. The graphics multiprocessor 234 shown is an illustrative example of a SIMT parallel processor. However, various types of SIMT parallel processors of different architectures may be included within processing cluster 214. One or more instances of graphics multiprocessor 234 may be included within processing cluster 214. The graphics multiprocessor 234 may process data, and the data crossbar 240 may be used to distribute the processed data to one of multiple possible destinations (including other shader units). The pipeline manager 232 may facilitate distribution of processed data by specifying destinations for the processed data to be distributed via the data crossbar 240.

Each graphics multiprocessor 234 within processing cluster 214 may include the same set of function execution logic (e.g., arithmetic logic unit, load-store unit, etc.). The function execution logic can be configured in a pipelined manner in which a new instruction can be issued before a previous instruction completes. The function execution logic supports a wide variety of operations including integer and floating point arithmetic, compare operations, Boolean operations, bit shifting, and computation of various algebraic functions. In one embodiment, different operations may be performed by the same functional unit hardware, and any combination of functional units may be present.

The instructions delivered to processing cluster 214 constitute a thread. A set of threads executing across a set of parallel processing engines is a thread group. The thread group executes the same program on different input data. Each thread within the thread group may be assigned to a different processing engine within graphics multiprocessor 234. The thread group may include fewer threads than the number of processing engines within graphics multiprocessor 234. When the thread group includes fewer threads than the number of processing engines, one or more of the processing engines may be idle during the cycles in which the thread group is being processed. The thread group may also include a greater number of threads than the number of processing engines within graphics multiprocessor 234. Processing may be performed on successive clock cycles when the thread group includes more threads than the number of processing engines within graphics multiprocessor 234. In one embodiment, multiple thread groups may be concurrently executing on graphics multiprocessor 234.

In one embodiment, graphics multiprocessor 234 includes an internal cache memory for performing load and store operations. In one embodiment, graphics multiprocessor 234 may relinquish internal caching and use cache memory within processing cluster 214 (e.g., L1 cache 308). Each graphics multiprocessor 234 also has access to the L2 cache within a partition unit (e.g., partition units 220A-220N of FIG. 2) that may be used to transfer data between threads and that is shared among all processing clusters 214. The graphics multiprocessor 234 may also have access to off-chip global memory, which may include one or more of local parallel processor memory and/or system memory. Any memory external to parallel processing unit 202 may be used as global memory. Embodiments (where processing cluster 214 includes multiple instances of graphics multiprocessor 234) may share common instructions and data, which may be stored in L1 cache 308.

Each processing cluster 214 may include an MMU 245 (memory management unit) configured to map virtual addresses into physical addresses. In other embodiments, one or more instances of MMU 245 may reside within memory interface 218 of FIG. 2. MMU 245 includes: a set of Page Table Entries (PTEs) for mapping virtual addresses of a tile (more discussion of tiling) to its physical addresses; and optionally a cache line index. MMU 245 may comprise an address Translation Lookaside Buffer (TLB) or cache that may reside within graphics multiprocessor 234 or L1 cache or processing cluster 214. The physical addresses are processed to distribute surface data access locality, allowing efficient request interleaving among partition units. The cache line index may be used to determine whether a request for a cache line is a hit or a miss.

In graphics and computing applications, processing cluster 214 may be configured such that each graphics multiprocessor 234 is coupled to a texture unit 236 for performing texture mapping operations, such as determining texture sample locations, reading texture data, and filtering texture data. Texture data is read from an internal texture L1 cache (not shown) or, in some embodiments, from an L1 cache within graphics multiprocessor 234, and fetched from an L2 cache, local parallel processor memory, or system memory, as needed. Each graphics multiprocessor 234 outputs processed tasks to data crossbar 240 to provide processed tasks to another processing cluster 214 for further processing or to store processed tasks in an L2 cache, local parallel processor memory, or system memory via memory crossbar 216. The preROP 242 (e.g., a pre-raster operations unit) is configured to receive data from the graphics multiprocessor 234, direct data to ROP units, which may be located with partition units (e.g., partition units 220A-220N of FIG. 2) as described herein. The preROP 242 unit may perform optimizations for color mixing, organize pixel color data, and perform address translation.

It will be appreciated that the core architecture described herein is illustrative and that variations and modifications are possible. Any number of processing units (e.g., graphics multiprocessor 234, texture unit 236, preROP 242, etc.) may be included within processing cluster 214. Further, although only one processing cluster 214 is shown, a parallel processing unit as described herein may include any number of instances of processing cluster 214. In one embodiment, each processing cluster 214 may be configured to operate independently of other processing clusters 214 using separate and distinct processing units, L1 caches, and the like.

FIG. 2D illustrates a graphics multiprocessor 234 according to one embodiment. In such embodiments, graphics multiprocessor 234 is coupled with pipeline manager 232 of processing cluster 214. Graphics multiprocessor 234 has an execution pipeline including, but not limited to: instruction cache 252, instruction unit 254, address mapping unit 256, register file 258, one or more General Purpose Graphics Processing Unit (GPGPU) cores 262, and one or more load/store units 266. GPGPU core 262 and load/store unit 266 are coupled with cache memory 272 and shared memory 270 via memory and cache interconnect 268.

In one embodiment, instruction cache 252 receives a stream of instructions to be executed from pipeline manager 232. The instructions are cached in instruction cache 252 and dispatched for execution by instruction unit 254. Instruction unit 254 may dispatch instructions as a group of threads (e.g., a bundle of threads (warp)), where each thread of the group of threads is assigned to a different execution unit within GPGPU core 262. An instruction may access any of the local, shared, or global address spaces by specifying an address within the unified address space. The address mapping unit 256 may be used to translate addresses in the unified address space into different memory addresses that may be accessed by the load/store unit 266.

Register file 258 provides a set of registers for the functional units of graphics multiprocessor 324. The register file 258 provides temporary storage for operands of the datapath connected to the functional units of the graphics multiprocessor 324 (e.g., GPGPU core 262, load/store unit 266). In one embodiment, register file 258 is divided among each of the functional units such that each functional unit is assigned a dedicated portion of register file 258. In one embodiment, the register file 258 is divided among different thread bundles executed by the graphics multiprocessor 324.

GPGPU cores 262 may each include a Floating Point Unit (FPU) and/or an integer Arithmetic Logic Unit (ALU) for executing instructions of graphics multiprocessor 324. Depending on the embodiment, GPGPU core 262 may be architecturally similar, or may be architecturally different. For example and in one embodiment, a first portion of the GPGPU core 262 includes single precision FPUs and integer ALUs, while a second portion of the GPGPU core includes double precision FPUs. In one embodiment, the FPU may implement the IEEE 754-. Graphics multiprocessor 324 may additionally include one or more fixed-function or special-function units to perform specific functions (such as copy rectangles or pixel blending operations). In one embodiment, one or more of the GPGPU cores may also include fixed or special function logic.

In one embodiment, GPGPU core 262 includes SIMD logic capable of executing a single instruction on multiple sets of data. In one embodiment, GPGPU core 262 may physically execute SIMD4, SIMD8, and SIMD16 instructions and logically execute SIMD1, SIMD2, and SIMD32 instructions. SIMD instructions for a GPGPU core may be generated by a shader compiler at compile time, or may be generated automatically when executing a program written and compiled for a Single Program Multiple Data (SPMD) or SIMT architecture. Multiple threads of a program configured for the SIMT execution model may be executed via a single SIMD instruction. For example and in one embodiment, eight SIMT threads performing the same or similar operations may be executed in parallel via a single SIMD8 logic unit.

Memory and cache interconnect 268 is an interconnection network that connects each of the functional units of graphics multiprocessor 234 to register file 258 and to shared memory 270. In one embodiment, memory and cache interconnect 268 is a crossbar interconnect that allows load/store unit 266 to implement load and store operations between shared memory 270 and register file 258. The register file 258 may operate at the same frequency as the GPGPU core 262, whereby data transfers between the GPGPU core 262 and the register file 258 are very low latency. Shared memory 270 may be used to enable communication between threads executing on functional units within graphics multiprocessor 234. Cache memory 272 may function as, for example, a data cache to cache texture data communicated between functional units and texture units 236. Shared memory 270 may also be used as a cache for program management. Threads executing on GPGPU core 262 may programmatically store data in shared memory in addition to the automatically cached data stored in cache memory 272.

3A-3B illustrate additional graphics multiprocessors according to embodiments. The illustrated graphics multiprocessors 325, 350 are a variation of the graphics multiprocessor 234 of fig. 2C. The illustrated graphics multiprocessors 325, 350 may be configured as Streaming Multiprocessors (SM) capable of executing a large number of execution threads simultaneously.

FIG. 3A illustrates a graphics multiprocessor 325, according to an additional embodiment. Graphics multiprocessor 325 contains multiple additional instances of execution resource units related to graphics multiprocessor 234 of FIG. 2D. For example, graphics multiprocessor 325 may include multiple instances of instruction units 332A-332B, register files 334A-334B, and texture units 344A-344B. Graphics multiprocessor 325 also includes multiple sets of graphics or compute execution units (e.g., GPGPU cores 336A-336B, GPGPU cores 337A-337B, GPGPU cores 338A-338B) and multiple sets of load/store units 340A-340B. In one embodiment, the execution resource units have a common instruction cache 330, texture and/or data cache memory 342, and a shared memory 346.

The various components may communicate via an interconnect structure 327. In one embodiment, interconnect fabric 327 includes one or more crossbar switches to enable communication between the various components of graphics multiprocessor 325. In one embodiment, interconnect structure 327 is a separate high-speed network fabric layer on which each component of graphics multiprocessor 325 is stacked. Components of graphics multiprocessor 325 communicate with remote components via interconnect structure 327. For example, GPGPU cores 336A-336B, 337A-337B, and 3378A-338B may each communicate with shared memory 346 via interconnect fabric 327. Interconnect fabric 327 may arbitrate communication within graphics multiprocessor 325 to ensure fair bandwidth allocation among components.

FIG. 3B illustrates a graphics multiprocessor 350, according to an additional embodiment. The graphics processor includes multiple sets of execution resources 356A-356D, where each set of execution resources includes multiple instruction units, register files, GPGPU cores, and load store units, as shown in FIG. 2D and FIG. 3A. The execution resources 356A-356D may work in concert with the texture units 360A-360D for texture operations while sharing the instruction cache 354 and the shared memory 362. In one embodiment, execution resources 356A-356D may share multiple instances of instruction cache 354 and shared memory 362, as well as texture and/or data cache memories 358A-358B. Various components may communicate via interconnect structure 352, which is similar to interconnect structure 327 of FIG. 3A.

Those skilled in the art will appreciate that the architectures depicted in FIGS. 1, 2A-2D, and 3A-3B are illustrative and not limiting with respect to the scope of the present embodiments. Thus, the techniques described herein may be implemented on any properly configured processing unit, including but not limited to one or more mobile application processors, one or more desktop or server Central Processing Units (CPUs), including multi-core CPUs, one or more parallel processing units, such as parallel processing unit 202 of fig. 2, and one or more graphics processors or application-specific processing units, without departing from the scope of the embodiments described herein.

In some embodiments, a parallel processor or GPGPU as described herein is communicatively coupled to a host/processor core to accelerate graphics operations, machine learning operations, pattern analysis operations, and various General Purpose Gpu (GPGPU) functions. The GPU may be communicatively coupled to the host processor/core by a bus or other interconnect (e.g., a high speed interconnect such as PCIe or NVLink). In other embodiments, the GPU may be integrated on the same package or chip as the core and communicatively coupled to the core via an internal processor bus/interconnect (i.e., internal to the package or chip). Regardless of the manner in which the GPU is connected, the processor core may allocate work to the GPU in the form of a sequence of commands/instructions contained in the work descriptor. The GPU then uses specialized circuitry/logic for efficiently processing these commands/instructions.

Techniques for GPU-to-host processor interconnection

FIG. 4A illustrates an exemplary architecture in which

multiple GPUs

410 and 413 are communicatively coupled to multiple

multicore processors

405 and 406 via high-speed links 440 and 443 (e.g., buses, point-to-point interconnects, etc.). In one embodiment, high speed link 440-443 supports communication throughputs of 4GB/s, 30GB/s, 80GB/s or higher, depending on the implementation. Various interconnect protocols may be used, including but not limited to PCIe 4.0 or 5.0 and NVLink 2.0. However, the underlying principles of the invention are not limited to any particular communication protocol or throughput.

Additionally, in one embodiment, two or more of the GPUs 410 & 413 are interconnected via high speed links 444 & 445, which may be implemented using the same or different protocols/links as those used for the high speed links 440 & 443. Similarly, two or more of the

multi-core processors

405 and 406 may be connected by a high speed link 433, which high speed link 433 may be a Symmetric Multiprocessor (SMP) bus operating at 20GB/s, 30GB/s, 120GB/s, or higher. Alternatively, all communications between the various system components shown in fig. 4A may be implemented using the same protocol/link (e.g., over a common interconnect fabric). As mentioned, however, the underlying principles of the invention are not limited to any particular type of interconnect technology.

In one embodiment, each of the

multicore processors

405 and 406 is communicatively coupled to the

processor memories

401 and 402 via the memory interconnects 430 and 431, respectively, and each of the

GPUs

410 and 413 is communicatively coupled to the

GPU memory

420 and 423 via the GPU memory interconnects 450 and 453, respectively. The memory interconnects 430 through 431 and 450 through 453 may utilize the same or different memory access techniques. By way of example and not limitation, processor memory 401 and

GPU memory

420 and 423 may be volatile memory, such as Dynamic Random Access Memory (DRAM) (including stacked DRAM), graphics DDR SDRAM (GDDR) (e.g., GDDR5, GDDR 6), or High Bandwidth Memory (HBM), and/or may be non-volatile memory, such as 3DXPoint or Nano-Ram. In one embodiment, some portion of the memory may be volatile memory and another portion may be non-volatile memory (e.g., using a two-level memory (2 LM) hierarchy).

As described below, although the

various processors

405 and 406 and

GPUs

410 and 413 may be physically coupled to the

specific memories

401 and 402 and 420 and 423, respectively, a unified memory architecture may be implemented in which the same virtual system address space (also referred to as an "effective address" space) is distributed across all of the various physical memories. For example, processor memories 401-402 may each comprise 64GB of system memory address space, and GPU memories 420-423 may each comprise 32GB of system memory address space (yielding a total of 256GB of addressable memory in this example).

FIG. 4B shows additional details for the interconnection between the multi-core processor 407 and the graphics acceleration module 446, in accordance with one embodiment. The graphics acceleration module 446 may include one or more GPU chips integrated on line cards coupled to the processor 407 via a high speed link 440. Alternatively, the graphics acceleration module 446 may be integrated on the same package or chip as the processor 407.

The illustrated processor 407 includes multiple cores 460A-460D each having a translation look-aside buffer 461A-461D and one or more caches 462A-462D. The core may include various other components for executing instructions and processing data (e.g., instruction fetch units, branch prediction units, decoders, execution units, reorder buffers, etc.), which are not shown to avoid obscuring the underlying principles of the invention. Caches 462A-462D may include level 1 (L1) and level 2 (L2) caches. Additionally, one or more shared caches 426 may be included in the cache hierarchy and shared by multiple sets of cores 460A-460D. For example, one embodiment of the processor 407 includes 24 cores each having its own L1 cache, twelve shared L2 caches, and twelve shared L3 caches. In the present embodiment, one of the L2 and L3 caches is shared by two adjacent cores. The processor 407 and the graphics accelerator integration module 446 are coupled to a system memory 441, which system memory 441 may include

processor memory

401 and 402.

Coherency is maintained for data and instructions stored in the various caches 462A-462D, 456 and system memory 441 via inter-core communication through a coherency bus 464. For example, each cache may have cache coherency logic/circuitry associated therewith to communicate over the coherency bus 464 in response to a detected read or write to a particular cache line. In one implementation, a cache snoop protocol is implemented over coherency bus 464 to snoop cache accesses. Cache snooping/coherency techniques are well understood by those skilled in the art and will not be described in detail herein to avoid obscuring the underlying principles of the invention.

In one embodiment, the proxy circuitry 425 communicatively couples the graphics acceleration module 446 to the coherency bus 464, allowing the graphics acceleration module 446 to join a cache coherency protocol as a peer of a core. In particular, interface 435 provides connectivity to the proxy circuit 425 through a high-speed link 440 (e.g., PCIe bus, NVLink, etc.), and interface 437 connects the graphics acceleration module 446 to the link 440.

In one implementation, the accelerator integrated circuit 436 provides cache management, memory access, context management, and interrupt management services on behalf of multiple

graphics processing engines

431, 432, N of the graphics acceleration module 446.

Graphics processing engines

431, 432, N may each comprise a separate Graphics Processing Unit (GPU). Alternatively,

graphics processing engines

431, 432, N may include different types of graphics processing engines within a GPU, such as graphics execution units, media processing engines (e.g., video encoders/decoders), samplers, and bit block transport (blit) engines. In other words, the graphics acceleration module may be a GPU with multiple graphics processing engines 431- > 432, N, or the graphics processing engines 431- > 432, N may be individual GPUs integrated on a common package, line card, or chip.

In one embodiment, the accelerator integrated circuit 436 includes a Memory Management Unit (MMU) 439 for performing various memory management functions, such as virtual-to-physical memory translation (also referred to as effective-to-real memory translation) and memory access protocols for accessing the system memory 441. The MMU 439 can also include a Translation Lookaside Buffer (TLB) (not shown) for caching virtual/valid-to-physical/real address translations. In one implementation, the cache 438 stores commands and data for efficient access by the graphics processing engines 431- > 432, N. In one embodiment, the data stored in cache 438 and

graphics memory

433 and 434, N is coherent with core caches 462A-462D, 456 and system memory 411. As mentioned, this may be accomplished via proxy circuitry 425, which proxy circuitry 425 participates in cache coherency mechanisms on behalf of cache 438 and

memories

433 and 434, N (e.g., sending updates to cache 438 (in connection with modification/access of cache lines on processor caches 462A-462D, 456), and receiving updates from cache 438).

A set of registers 445 stores context data for threads executed by the graphics processing engines 431-432, N, and a context management circuit 448 manages thread contexts. For example, the context management circuitry 448 may perform save and restore operations during a context switch to save and restore the context of various threads (e.g., where a first thread is saved and a second thread is stored such that the second thread may be executed by the graphics processing engine). For example, at context switch, the context management circuitry 448 may store the current register value to an assigned region in memory (e.g., identified by a context pointer). It may then restore the register values upon returning to the context. In one embodiment, interrupt management circuit 447 receives and processes interrupts received from system devices.

In one implementation, virtual/effective addresses from graphics processing engine 431 are translated to real/physical addresses in system memory 411 by MMU 439. One embodiment of the accelerator integrated circuit 436 supports multiple (e.g., 4, 8, 16) graphics accelerator modules 446 and/or other accelerator devices. The graphics accelerator module 446 may be dedicated to a single application executing on the processor 407 or may be shared among multiple applications. In one embodiment, a virtualized graphics execution environment is presented in which the resources of graphics processing engine 431- > 432, N are shared with multiple applications or Virtual Machines (VMs). The resources may be subdivided into "slices" that are assigned to different VMs and/or applications (based on processing requirements and priorities associated with the VMs and/or applications).

Thus, the accelerator integrated circuit acts as a bridge to the system for the graphics acceleration module 446 and provides address translation and system memory caching services. Additionally, accelerator integrated circuit 436 may provide a virtualization facility for the host processor to manage interrupts, memory management, and virtualization of the graphics processing engine.

Since the hardware resources of graphics processing engine 431-432, N are explicitly mapped to the real address space seen by host processor 407, any host processor can directly address these resources using valid address values. In one embodiment, one function of the accelerator integrated circuit 436 is the physical separation of the graphics processing engines 431-432, N, such that they appear to the system as independent units.

As mentioned, in the illustrated embodiment, one or more graphics memories 433- < - > 434, M are coupled to each of the graphics processing engines 431- < - > 432, N, respectively. Graphics memories 433-434, M store instructions and data being processed by each of graphics processing engines 431-432, N. Graphics memories 433-434, M may be volatile memories such as DRAM (including stacked DRAM), GDDR memories (e.g., GDDR5, GDDR 6), or HBM, and/or may be non-volatile memories such as 3D XPoint or Nano-Ram.

In one embodiment, to reduce data traffic on link 440, a biasing technique is used to ensure that the data stored in graphics memory 433-. Similarly, the biasing mechanism attempts to save the data required by the core (and preferably not graphics processing engine 431-432, N) within system memory 411 and the core's caches 462A-462D, 456.

Fig. 4C illustrates another embodiment in which accelerator integrated circuit 436 is integrated within processor 407. In the present embodiment, graphics processing engines 431-432, N communicate directly to accelerator integrated circuit 436 over high speed link 440 via interface 437 and interface 435 (again, which may utilize any form of bus or interface protocol). The accelerator integrated circuit 436 may perform the same operations as those described for fig. 4B, but potentially at higher throughput in view of its close proximity to the coherency bus 462 and caches 462A-462D, 426.

One embodiment supports different programming models, including a dedicated process programming model (without graphics acceleration module virtualization) and a shared programming model (with virtualization). Which may include a programming model controlled by the accelerator integrated circuit 436 and a programming model controlled by the graphics acceleration module 446.

In one embodiment of the dedicated process model, the graphics processing engines 431-432, N are dedicated to a single application or process under a single operating system. A single application can aggregate (channel) other application requests to graphics engine 431- > 432, N, providing virtualization within the VM/partition.

In the dedicated process programming model, the graphics processing engine 431-432, N may be shared by multiple VM/application partitions. The shared model requires a hypervisor to virtualize the graphics processing engines 431- > 432, N to allow access by each operating system. For a single partition system without a hypervisor, graphics processing engines 431-432, N are owned by the operating system. In both cases, the operating system may virtualize the graphics processing engine 431- > 432, N to provide access to each process or application.

For the shared programming model, the graphics acceleration module 446 or the individual graphics processing engines 431- > 432, N use a process handle (process handle) to select a process element (process element). In one embodiment, the process elements are stored in system memory 411 and are addressable using effective to real address translation techniques described herein. The process handle may be an implementation-specific value that is provided to the host process when its context (that is, invoking the system software to add a process element to the process element linked list) is registered with the graphics processing engine 431-432, N. The lower 16 bits of the process handle may be the offset of the process element within the linked list of process elements.

Fig. 4D illustrates an exemplary accelerator integration slice 490. As used herein, a "slice" includes a designated portion of the processing resources of accelerator integrated circuit 436. An application effective address space 482 within system memory 411 stores a process element 483. In one embodiment, the process element 483 is stored in response to a GPU call (invocation)481 from an application 480 executing on the processor 407. The process element 483 contains the process state for the corresponding application 480. Work Descriptor (WD) 484 included in process element 483 may be a single job requested by an application or may include a pointer to a job queue. In the latter case, WD484 is a pointer to a queue of job requests in application's address space 482.

The graphics acceleration module 446 and/or the individual graphics processing engines 431-432, N may be shared by all processes or a subset of processes in the system. Embodiments of the present invention include infrastructure for setting up a process state and sending WD484 to graphics acceleration module 446 to begin operations in a virtualized environment.

In one implementation, the dedicated process programming model is implementation specific. In this model, a single process owns either the graphics acceleration module 446 or the individual graphics processing engine 431. Since the graphics acceleration module 446 is owned by a single process, the hypervisor initializes the accelerator integrated circuits 436 for the owned partitions, and the operating system initializes the accelerator integrated circuits 436 for the owned processes (at the time the graphics acceleration module 446 is assigned).

In operation, WD extraction unit 491 in accelerator integration slice 490 extracts a next WD484, which next WD484 includes an indication of work to be done by one of the graphics processing engines of graphics acceleration module 446. Data from WD484 may be stored in registers 445 and used by MMU 439, interrupt management circuitry 447, and/or context management circuitry 446 as shown. For example, one embodiment of MMU 439 includes a segment/page walk circuit (walk circuit) for accessing segment/page tables 486 within OS virtual address space 485. The interrupt manager circuit 447 may process interrupt events 492 received from the graphics acceleration module 446. When performing graphics operations, the effective addresses 493 generated by graphics processing engines 431- + 432, N are translated to real addresses by MMU 439.

In one embodiment, the same set of registers 445 are replicated for each graphics processing engine 431- & 432, N and/or graphics acceleration module 446, and may be initialized by a hypervisor or operating system. Each of these copied registers may be included in the accelerator integration slice 490. Exemplary registers that may be initialized by the hypervisor are shown in table 1.

TABLE 1 hypervisor initialized registers

1	Slice control register
		2	Process area pointer for Real Address (RA) scheduling
3	Permission mask override register
		4	Interrupt vector table entry offset
5	Interrupt vector table entry restriction
		6	Status register
7	Logical partition ID
		8	Real Address (RA) hypervisor accelerator utilizing record pointers
9	Storage description register

Exemplary registers that may be initialized by the operating system are shown in table 2.

TABLE 2 registers for operating System initialization

1	Process and thread identification
		2	Effective Address (EA) context save/restore pointer
3	Virtual Address (VA) accelerator utilizing record pointers
		4	Virtual Address (VA) storage segment table pointer
5	Authority masking
		6	Work descriptor

In one embodiment, each WD484 is specific to a particular graphics acceleration module 446 and/or graphics processing engine 431-. It contains all the information required by the graphics processing engine 431-432, N to complete its work, or it may be a pointer to the memory location of the command queue where the application has set up the work to be completed.

FIG. 4E illustrates additional details for one embodiment of the sharing model. The present embodiment includes a hypervisor real address space 498 in which a process element list 499 is stored. The hypervisor real address space 498 is accessible via a hypervisor 496, which hypervisor 496 virtualizes the graphics acceleration module engine for the operating system 495.

The shared programming model allows all processes or a subset of processes from all partitions or a subset of partitions in the system to use the graphics acceleration module 446. There are two programming models in which the graphics acceleration module 446 is shared by multiple processes and partitions: time slice sharing and graphics directed sharing.

In this model, hypervisor 496 owns graphics acceleration module 446 and makes its functionality available to all operating systems 495. For graphics acceleration module 446 to support virtualization by hypervisor 496, graphics acceleration module 446 may comply with the following requirements: 1) the application's job requests must be autonomous (that is, no state needs to be maintained between jobs), or the graphics acceleration module 446 must provide a context save and restore mechanism. 2) The job requests of the application (including any translation faults) are guaranteed to complete within a specified amount of time by the graphics acceleration module 446, or the graphics acceleration module 446 provides the ability to preempt processing of the job. 3) When operating in the directed sharing programming model, graphics acceleration module 446 must ensure fairness between processes.

In one embodiment, for the shared model, the application 480 is required to make operating system 495 system calls with a graphics acceleration module 446 type, a Work Descriptor (WD), an Authority Mask Register (AMR) value, and a context save/restore area pointer (CSRP). Graphics acceleration module 446 types describe targeted acceleration functionality for system calls. The graphics acceleration module 446 type may be a system specific value. WD is formatted specifically for graphics acceleration module 446 and may take the form of graphics acceleration module 446 commands, effective address pointers to user-defined structures, effective address pointers to command queues, or any other data structure used to describe work to be done by graphics acceleration module 446. In one embodiment, the AMR value is the AMR state to be used for the current process. The values passed to the operating system are similar to the application setting AMR. If the accelerator integrated circuit 436 and graphics acceleration module 446 implementation do not support a User Authority Mask Override Register (UAMOR), the operating system may apply the current UAMOR value to the AMR value (before passing AMR in the hypervisor call). Optionally, the hypervisor 496 may apply a current privilege mask override register (AMOR) value (before placing AMR into the process element 483). In one embodiment, CSRP is one of registers 445 that contains the effective address of a region in the application's address space 482 for use in causing graphics acceleration module 446 to save and restore context state. This pointer is optional if it is not required to save state between jobs or when a job is preempted. The context save/restore area may be fixed (pined) system memory.

Upon receiving the system call, the operating system 495 may verify that the application 480 is registered and has been given the right to use the graphics acceleration module 446. Operating system 495 then calls hypervisor 496 with the information shown in table 3.

TABLE 3-OS to hypervisor Call parameters

1	Work Descriptor (WD)
		2	Permission mask register (AMR) value (potentially masked)
3	Effective Address (EA) context save/restore area pointer (CSRP)
		4	Process ID (PID) and optional Thread ID (TID)
5	Virtual Address (VA) accelerator utilizing a record pointer (AURP)
		6	Virtual address Storing Segment Table Pointer (SSTP)
7	Logic Interruption Service Number (LISN)

Upon receiving the hypervisor call, hypervisor 496 verifies that operating system 495 is registered and has been given authority to use graphics acceleration module 446. Hypervisor 496 then places process element 483 into the linked list of process elements for the corresponding graphics acceleration module 446 type. The process elements may include the information shown in table 4.

Table 4-Process element information

1	Work Descriptor (WD)
		2	Permission mask register (AMR) value (potentially masked)
3	Effective Address (EA) context save/restore area pointer (CSRP)
		4	Process ID (PID) and optional Thread ID (TID)
5	Virtual Address (VA) accelerator utilizing a record pointer (AURP)
		6	Virtual address Storing Segment Table Pointer (SSTP)
7	Logic Interruption Service Number (LISN)
		8	Interrupt vector table derived from hypervisor call parameters
9	Status Register (SR) value
		10	Logical Partition ID (LPID)
11	Real Address (RA) hypervisor accelerator utilizing record pointers
		12	Storage Descriptor Register (SDR)

In one embodiment, the hypervisor initializes the plurality of accelerator integration slices 490 registers 445.

As shown in FIG. 4F, one embodiment of the invention employs unified memory addressable via a common virtual memory address space for accessing physical processor memory 401 and

GPU memory

420 and 423. In such an implementation, the operations performed on the

GPUs

410 and 413 utilize the same virtual/effective memory address space to access the

processor memories

401 and 402 and vice versa, thereby simplifying programmability. In one embodiment, a first portion of the virtual/effective address space is allocated to processor memory 401, a second portion is allocated to second processor memory 402, a third portion is allocated to GPU memory 420, and so on. The entire virtual/effective memory space (sometimes referred to as the effective address space) is thus distributed across each of the processor memory 401 and the

GPU memory

402 and 423, allowing any processor or GPU to access any physical memory (with virtual addresses mapped to that memory).

In one embodiment, the bias/coherency management circuits 494A-494E within one or more of the MMUs 439A-439E ensure cache coherency between the host processor (e.g., 405) and the caches of the

GPUs

410 and 413 and implement a biasing technique that indicates the physical memory in which certain types of data should be stored. Although multiple instances of bias/coherency management circuits 494A-494E are shown in FIG. 4F, the bias/coherency circuits may be implemented within one or more MMUs of host processor 405 and/or within accelerator integrated circuit 436.

One embodiment allows the GPU-attached memory 420 to be accessed and mapped 423 as part of system memory using a Shared Virtual Memory (SVM) technique without suffering from the typical performance drawbacks associated with full system cache coherency. The ability of the GPU attached memory 420-423 to be accessed as system memory without heavy cache coherency overhead provides a beneficial operating environment for GPU offloading. This arrangement allows the host processor 405 software to set operands and access computational results without the overhead of conventional I/O DMA data copying. Such traditional copying involves driver calls, interrupts, and memory mapped I/o (mmio) accesses, all of which are inefficient relative to simple memory accesses. Meanwhile, the ability to access GPU-attached memory 420-423 without cache coherency overhead can be critical to the execution time of the offloaded computations. In the case of substantial streaming write memory traffic, for example, the cache coherency overhead can significantly reduce the effective write bandwidth seen by the

GPU

410 and 413. The efficiency of operand setup, the efficiency of result access, and the efficiency of GPU computations all play a role in determining the effectiveness of GPU offload.

In one implementation, the selection between GPU biasing and host processor biasing is driven by a bias tracker data structure. For example, a bias table may be used, which may be a page granularity structure (i.e., controlled at the granularity of a memory page) that includes 1 or 2 bits per GPU attached memory page. The bias table may be implemented in a stolen (stolen) memory range of one or more GPU-attached memories 420-423 with or without a bias cache (e.g., a frequently/recently used entry for caching the bias table) in GPU 410-413. Alternatively, the entire bias table may be maintained within the GPU.

In one implementation, the bias table entries associated with each access to the GPU attached

memory

420 and 423 are accessed prior to actual access to the GPU memory, causing the following operations. First, the local requests from the

GPUs

410 and 413 to find their pages in GPU offsets are forwarded directly to the corresponding

GPU memories

420 and 423. Local requests from the GPU to find their pages in the host bias are forwarded to the processor 405 (e.g., over a high speed link as discussed above). In one embodiment, a request from the processor 405 to find a requested page in the host processor bias completes a request similar to a normal memory read. Alternatively, the request for GPU-biased pages may be forwarded to

GPU

410 and 413. Then, if the GPU is not currently using the page, the GPU may transition the page to host processor bias.

The bias state of a page may be changed by a software-based mechanism, a hardware-assisted software-based mechanism, or a purely hardware-based mechanism for a limited set of cases.

One mechanism for changing the bias state employs an API call (e.g., OpenCL) that in turn calls the device driver of the GPU, which in turn sends a message (or enqueue command descriptor) to the GPU instructing it to change the bias state and perform a cache flush operation in the host for some transitions. The cache flush operation is needed for the transition from host processor 405 bias to GPU bias, but not for the reverse transition.

In one embodiment, cache coherency is maintained by temporarily rendering GPU offset pages that are not cacheable by the host processor 405. To access these pages, the processor 405 may request access from the GPU 410, which may or may not grant access immediately (depending on the implementation). Thus, to reduce communication between the processor 405 and the GPU 410, it is advantageous to ensure that GPU offset pages are those pages that are required by the GPU but not by the host processor 405 (and vice versa).

Graphics processing pipeline

FIG. 5 illustrates a graphics processing pipeline 500 according to an embodiment. In one embodiment, a graphics processor may implement the illustrated graphics processing pipeline 500. The graphics processor may be included within a parallel processing subsystem as described herein, such as parallel processor 200 of fig. 2, which in one embodiment is a variation of parallel processor(s) 112 of fig. 1. Various parallel processing systems may implement graphics processing pipeline 500 via one or more instances of a parallel processing unit (e.g., parallel processing unit 202 of fig. 2) as described herein. For example, a shader unit (e.g., graphics multiprocessor 234 of fig. 3) may be configured to perform the functions of one or more of vertex processing unit 504, tessellation control processing unit 508, tessellation evaluation processing unit 512, geometry processing unit 516, and fragment/pixel processing unit 524. The functions of data assembler 502, primitive assemblers 506, 514, 518, tessellator unit 510, rasterizer 522, and raster operations unit 526 may also be performed by other processing engines and corresponding partition units (e.g., partition units 220A-220N of FIG. 2) within a processing cluster (e.g., processing cluster 214 of FIG. 3). Graphics processing pipeline 500 may also be implemented using dedicated processing units for one or more functions. In one embodiment, one or more portions of graphics processing pipeline 500 may be executed by parallel processing logic within a general purpose processor (e.g., a CPU). In one embodiment, one or more portions of graphics processing pipeline 500 may access on-chip memory (e.g., as parallel processor memory 222 in FIG. 2) via memory interface 528, which memory interface 528 may be an example of memory interface 218 of FIG. 2.

In one embodiment, data assembler 502 is a processing unit that collects vertex data for surfaces and primitives. Data populator 502 then outputs vertex data, including the vertex attributes, to vertex processing unit 504. Vertex processing unit 504 is a programmable execution unit that executes a vertex shader program, lighting (lighting) as specified by the vertex shader program, and transforms vertex data. Vertex processing unit 504 reads data stored in cache, local, or system memory for use in processing the vertex data, and vertex processing unit 504 may be programmed to transform the vertex data from an object-based coordinate representation to world space coordinate space or normalized device coordinate space.

A first instance of primitive assembler 506 receives vertex attributes from vertex processing unit 504. Primitive assembler 506 reads the stored vertex attributes as needed and constructs graphics primitives for processing by tessellation control processing unit 508. Graphics primitives include triangles, line segments, points, patches (patches), and so forth as supported by various graphics processing Application Programming Interfaces (APIs).

The tessellation control processing unit 508 treats the input vertices as control points for the geometric patches. The control points are transformed from an input representation from the patches (e.g., the basis of the patches) to a representation suitable for use in surface evaluation by the tessellation evaluation processing unit 512. The tessellation control processing unit 508 may also calculate tessellation factors for the edges of the geometric patches. The tessellation factor is applied to a single edge and the view-dependent level of detail associated with that edge is quantified. Tessellation unit 510 is configured to receive tessellation factors for edges of a patch and tessellate the patch into a plurality of geometric primitives, such as line, triangle, or quadrilateral primitives, which are passed to tessellation evaluation processing unit 512. The tessellation evaluation processing unit 512 operates on the parameterized coordinates of the subdivided patches to generate a surface representation and vertex attributes for each vertex associated with the geometric primitive.

A second instance of primitive assembler 514 receives the vertex attributes from tessellation evaluation processing unit 512 (which reads the stored vertex attributes as needed), and constructs the graphics primitives for processing by geometry processing unit 516. Geometry processing unit 516 is a programmable execution unit that executes a geometry shader program to transform graphics primitives received from primitive assembler 514 as specified by the geometry shader program. In one embodiment, geometry processing unit 516 is programmed to subdivide a graphics primitive into one or more new graphics primitives and to compute parameters for rasterizing the new graphics primitives.

In some embodiments, geometry processing unit 516 may add or delete elements in the geometry stream. Geometry processing unit 516 outputs parameters and vertices that specify new graphics primitives to primitive assembler 518. Primitive assembler 518 receives the parameters and vertices from geometry processing unit 516 and constructs graphics primitives for processing by viewport scale, sort, and clip unit 520. Geometry processing unit 516 reads data stored in parallel processor memory or system memory for use in processing geometry data. Viewport scale, cull, and clip unit 520 performs clipping, culling, and viewport scaling and outputs processed graphics primitives to rasterizer 522.

Rasterizer 522 may perform depth culling and other depth-based optimizations. Rasterizer 522 also performs scan conversion on the new graphics primitives to generate fragments and outputs those fragments and associated coverage data to fragment/pixel processing unit 524. Fragment/pixel processing unit 524 is a programmable execution unit configured to execute fragment shader programs or pixel shader programs. Fragment/pixel processing unit 524 transforms the fragments or pixels received from rasterizer 522 as specified by a fragment or pixel shader program. For example, the fragment/pixel processing unit 524 may be programmed to perform operations including, but not limited to, texture mapping, shading, blending, texture correction, and perspective correction to generate shaded fragments or pixels that are output to the raster operations unit 526. Fragment/pixel processing unit 524 may read data stored in a parallel processor memory or a system memory for use in processing fragment data. Fragment or pixel shader programs may be configured to color at sample, pixel, tile, or other granularity (depending on the sampling rate configured for the processing unit).

Raster operations unit 526 is a processing unit that performs raster operations including, but not limited to, stencil printing, z-testing, blending, and the like, and outputs pixel data as processed graphics data for storage in graphics memory (e.g., parallel processor memory 222 as in fig. 2 and/or system memory 104 as in fig. 1) for display on the one or more display devices 110 or for further processing by parallel processor(s) 112 or one of the one or more processors 102. In some embodiments, raster operations unit 526 is configured to compress z or color data written to memory and decompress z or color data read from memory.

Graphics system with additional context examples

Turning now to fig. 6, an embodiment of an electronic processing system 600 may include an application processor 611, a persistent storage medium 612 communicatively coupled to the application processor 611, and a graphics subsystem 613 communicatively coupled to the application processor 611. Graphics subsystem 613 may include a first graphics engine 614 for processing graphics workloads and a second graphics engine 615 for offloading at least a portion of the graphics workload from first graphics engine 614. For example, the second graphics engine 615 may include a low precision compute engine (e.g., as described in more detail below). In some embodiments, the system 600 may include a wearable device for housing the second graphics engine 615 (e.g., as described in more detail below).

Embodiments of each of the above application processor 611, persistent storage medium 612, graphics subsystem 613, first graphics engine 614, second graphics engine 615, and other system components may be implemented in hardware, software, or any suitable combination thereof. For example, a hardware implementation may include configurable logic, such as, for example, Programmable Logic Arrays (PLAs), FPGAs, Complex Programmable Logic Devices (CPLDs), or fixed functionality logic hardware using circuit technologies such as, for example, ASICs, Complementary Metal Oxide Semiconductor (CMOS) or transistor-transistor logic (TTL) technologies, or any combination thereof. Alternatively or additionally, these components may be implemented in one or more modules as a set of logical instructions stored in a machine-or computer-readable storage medium (such as Random Access Memory (RAM), Read Only Memory (ROM), programmable ROM (prom), firmware, flash memory, etc.) to be executed by a processor or computing device. For example, computer program code for performing component operations may be written in any combination of one or more operating system-applicable/suitable programming languages, including an object oriented programming language such as PYTHON, PERL, JAVA, SMALLTALK, C + +, C #, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages.

For example, system 600 may include similar components and/or features as system 100, further configured to offload graphics work to a second graphics engine. For example, graphics subsystem 613 may include similar components and/or features as parallel processor 200, further configured with a second graphics engine as described herein. The system 600 may also be adapted to work with stereo head mounted systems such as, for example, the systems described below in connection with fig. 11-15.

Turning now to fig. 7, an embodiment of a graphics device 700 may include a first graphics engine 721 to process a graphics workload and a second graphics engine 722 to offload at least a portion of the graphics workload from the first graphics engine 721. For example, the second graphics engine may include a low precision compute engine 723. In some embodiments, the low-precision compute engine may be configured to perform at least one of time warping (e.g., which may also be referred to as re-projection in some embodiments), spatial warping (e.g., or frame rate up-conversion in some embodiments), and machine learning. The apparatus 700 may also include a second context for the second graphics engine that is independent of the first context for the first graphics engine.

In some embodiments, the apparatus 700 may further include a wearable device for housing the second graphics engine 722. The second graphics engine 722 may be further configured to offload rendering work from the first graphics engine 721. For example, the wearable device may include a head mounted display, and the second graphics engine 722 may be configured to offload recessed (foveated) rendering work from the first graphics engine 721.

Embodiments of each of the above first graphics engine 721, second graphics engine 722, low precision computing engine 723, and other components of the device 700 may be implemented in hardware, software, or any combination thereof. For example, part or all of device 700 may be implemented as part of parallel processor 200, further configured with a second graphics engine as described herein. The device 700 may also be adapted to work with stereo head mounted systems such as, for example, the systems described below in connection with fig. 11-15. For example, a hardware implementation may include configurable logic, such as, for example, PLA, FPGA, CPLD, or fixed functionality logic hardware using circuit technologies such as, for example, ASIC, CMOS, or TTL technologies, or any combination thereof. Alternatively or additionally, these components may be implemented in one or more modules as a set of logical instructions stored in a machine-or computer-readable storage medium (such as RAM, ROM, PROM, firmware, flash memory, etc.) to be executed by a processor or computing device. For example, computer program code for performing component operations may be written in any combination of one or more operating system-applicable/suitable programming languages, including an object oriented programming language such as PYTHON, PERL, JAVA, SMALLTALK, C + +, C #, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages.

Turning now to fig. 8A-8C, an embodiment of a method 800 may include: at block 831, processing the graphics workload with the first graphics engine; and at block 832, offloading at least a portion of the graphics workload from the first graphics engine to the second graphics engine. The method 800 may also include: at block 833, a low precision computing engine is provided for the second graphics engine. For example, the method 800 may include: at block 834, performing at least one of time warping, spatial warping, and machine learning with a low precision computing engine; and/or at block 835, providing a second context for the second graphics engine that is independent of the first context for the first graphics engine.

In some embodiments, the method 800 may further include: at block 836, a wearable device for housing a second graphics engine is provided. The method 800 may also include: at block 837, the rendering job is offloaded from the first graphics engine to the second graphics engine. For example, the method 800 may include: at block 838, providing a head mounted display for mounting the second graphics engine; and at block 839, offloading the foveated rendering work from the first graphics engine to the second graphics engine.

Embodiments of method 800 may be implemented in a system, device, GPU, PPU, or graphics processor pipeline device, such as, for example, those described herein. More specifically, a hardware implementation of method 800 may include configurable logic, such as, for example, PLA, FPGA, CPLD, or fixed functionality logic hardware using circuit technologies such as, for example, ASIC, CMOS, or TTL technologies, or any combination thereof. Alternatively or additionally, method 800 may be implemented in one or more modules as a set of logical instructions stored in a machine-or computer-readable storage medium (such as RAM, ROM, PROM, firmware, flash memory, etc.) to be executed by a processor or computing device. For example, computer program code for performing component operations may be written in any combination of one or more operating system-applicable/suitable programming languages, including an object oriented programming language such as PYTHON, PERL, JAVA, SMALLTALK, C + +, C #, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. For example, method 800 may be implemented on a computer-readable medium, as described below in connection with examples 18-24.

For example, an embodiment or portion of method 800 may be implemented in an application (e.g., through an API) or driver software. Other embodiments or portions of method 800 may be implemented with specialized code (e.g., shaders) to be executed on the GPU. Other embodiments or portions of method 800 may be implemented in fixed-function logic or dedicated hardware (e.g., in a GPU).

Low precision compute engine examples

Advantageously, some embodiments may provide a fixed function warp engine for Virtual Reality (VR) to avoid 3D pipeline context switching. For example, some embodiments may reduce the overhead of Execution Unit (EU) load balancing by using fixed function logic to perform time-warping when using VR. Advantageously, some embodiments may not require any context switch. Providing additional asynchronous engines may also eliminate complex asynchronous computations for other aspects of the time warp operation when context switching is involved. For example, some embodiments may provide hardware blocks to implement time-warping (in addition to conventional 3D hardware) to avoid 3D pipeline context switching. The hardware block may contain a dedicated cache for time warp data.

Turning now to fig. 9, graphics system 900 may include a 3D pipeline 901 for processing graphics workloads to generate frame information for an nth frame (3D frame [ n ]). The system 900 may offload the time warp operation 903 to a dedicated low precision compute engine 905 (e.g., hardware and processing costs dedicated to the time warp operation 903). Low-precision compute engine 905 may share memory interface 907 with 3D pipeline 901. The time warping operation 903 may generate an alternate frame for the next frame (TW frame [ n +1 ]). The selector 909 may select between the next regular 3D frame (3D frame [ n +1]) and the candidate frame for the next frame (TW frame [ n +1]) based on the detected condition. For example, if the next regular 3D frame is not ready after a predetermined amount of time (e.g., 20 ms), selector 909 may select an alternate frame.

Some embodiments may take all or most of the functionality of time-warping operations that might otherwise be performed on a GPU/API or the like, and provide a dedicated asynchronous computing mechanism for performing time-warping operations. Advantageously, the GPU need not be distributed for time-warping, as there is a dedicated engine for time-warping. For example, the time-warping engine may advantageously include a low-power, fixed-point image processing/computation engine, as floating points may not be needed for time-warping operations. Some embodiments may advantageously use less power by performing time-warping operations on a low-precision compute engine instead of a more fully featured 3D pipeline. The low precision computing engine may be a fixed function engine, but more preferably may be a programmable fixed point general purpose unit that may also be used for spatial warping, machine learning, or other processing suitable for the low precision computing engine.

The architecture for the low precision compute engine may be similar to the GPU architecture, but with a smaller number of compute units and all integer arithmetic (the various fixed function stages of the GPU may be omitted). The low-precision compute engine may contain its own cache, etc., and may have a separate command stream, but share the same memory interface with the GPU. For example, a low precision compute engine may have its own command stream so that time-warping may be invoked by a separate task queue. The individual queues may be provided to individual engines. Some embodiments may include separate low precision compute engines per GPU and may scale with the number of GPUs. The command streamer may be external to the GPU so it can stream to any resource internal to the GPU. Advantageously, some embodiments may reduce motion-to-photon latency.

Wearable device example

Some embodiments may advantageously provide gaze information for improved or optimized second stage time warping on a Head Mounted Display (HMD). Some embodiments may improve or optimize time warping on the HMD to reduce processing on the HMD, providing power and/or latency benefits. For example, portions of the GPU or graphics pipeline may be replicated on the HMD to handle more complex processing. In some embodiments, the foveated rendering task may be offloaded to the HMD. In some embodiments, the wearable device may alternatively or additionally include a shoulder-mounted display and/or a neck-mounted display.

For time warping, foveal rendering may not be as efficient due to the need for larger foveal radii (e.g., to cover potential head activity). By performing the foveal rendering on the HMD side, some embodiments may improve or optimize the foveal rendering. Performing a recessed rendering on the HMD side may account for the larger radius used for time warping. The first stage may refer to a time-warped transitional aspect, while the second stage may refer to a recessed rendering on the HMD. The first stage may not be as efficient on the host side because the host may maintain higher precision and larger buffers than needed for time warp operations.

Turning now to fig. 10, the graphics system 1000 may include a host side 1011 communicatively coupled to an HMD side 1012 (e.g., the communication may be wired or wireless). Graphics system 1000 may offload a foveated rendering task 1013 to HMD side 1012. HMD side 1012 may improve or optimize the foveated rendering task 1013a for time warping. For example, when combining a foveated rendering task with time warping, some embodiments may define an elliptical concavity (fovea) aligned with the direction of motion. The host side 1011 may still perform some time warping and/or foveal rendering operations. But by boosting processing power on the HMD side 1012, some embodiments may be able to offload more, and/or balance graphics workload.

Some other HMD architectures may simply include a display port and some translation hardware to send translation information to the display panel. Some embodiments may advantageously include a graphics data interface (e.g., more like Universal Serial Bus (USB)), where graphics may be transferred as data instead of as a stream. Some embodiments may include additional computing power on the HMD side 1012 to process/post-process the data before sending it to the display. For example, the HMD side 1012 may include media decoding/encoding capabilities. For time warping operations in the HMD side 1012, additional capabilities may include barrel distortion (barrel distortion) correction, aberration correction, and/or other synthesizer capabilities that migrate to the HMD side 1012. The host side may also retain those functions, but if the HMD side 1012 has the capability, the system 100 may offload some more work to the HMD side 1012. Some rasterization capability may also be migrated to the HMD side 1012. The specific zoning between transactions that are performed on the host side 1011 and transactions that are performed on the HMD side 1012 may depend on the specific workload and/or processing capabilities of the HMD side 1012. With more processing power on the HMD side 1012, the system 1000 may only need to transfer delta information for certain frames (e.g., only modified pixel blocks are transferred from the host side 1011 to the HMD side 1012).

Overview of head mounted display System

Fig. 11 shows a head-mounted display (HMD) system 1100 being worn by a user while experiencing an immersive environment, such as, for example, a Virtual Reality (VR) environment, an Augmented Reality (AR) environment, a multiplayer three-dimensional (3D) game, and so forth. In the example shown, one or more straps 1120 hold the frame 1102 of the HMD system 1100 in front of the user's eyes. Accordingly, the left-eye display 1104 is positioned to be viewed by the left eye of the user and the right-eye display 1106 is positioned to be viewed by the right eye of the user. In some examples, such as, for example, a smartphone worn by a user, left-eye display 1104 and right-eye display 1106 may alternatively be integrated into a single display. In the case of AR, the

displays

1104, 1106 may be see-through displays that allow the user to view the physical environment while other rendered content (e.g., avatars, informational annotations, heads-up displays/HUDs) is presented over the real-time feed of the physical environment.

In one example, the frame 1102 includes a bottom left view camera 1108 to capture images from an area generally located in front of the user and below the left eye (e.g., a left hand gesture). Further, the bottom right view camera 1110 may capture images from an area generally in front of the user and below the right eye (e.g., a right hand gesture). The illustrated frame 1102 also includes a left front looking camera 1112 and a right front looking camera 1114 to capture images in front of the user's left and right eyes, respectively. The frame 1102 may also include a left-view camera 1116 to capture images from an area to the left of the user and a right-view camera 1118 to capture images from an area to the right of the user.

Images captured by

cameras

1108, 1110, 1112, 1114, 1116, 1118, which may have overlapping fields of view, may be used to detect gestures made by a user and analyze and/or render external environments on

displays

1104, 1106. In one example, the detected gestures are used by a graphics processing architecture (e.g., internal and/or external) to render and/or control a virtual representation of a user in a 3D game. Indeed, the overlapping fields of view may enable capture of gestures made by other individuals (e.g., in a multiplayer game), where the gestures of the other individuals may also be used to render/control the immersive experience. The overlapping fields of view may also enable the HMD system 1100 to automatically detect obstructions or other hazards in the vicinity of the user. Such methods are particularly advantageous in Advanced Driver Assistance System (ADAS) applications.

In one example, the lower left view camera 1108 and the lower right view camera 1110 provided with overlapping fields of view provide stereoscopic views with increased resolution. The increased resolution may in turn enable very similar user movements to be distinguished from each other (e.g., with sub-millimeter accuracy). The result may be improved performance of the HMD system 1100 with respect to reliability. In fact, the illustrated solution is useful in a wide variety of applications, such as, for example, coloring information in AR settings, exchanging virtual tools/devices between users in a multi-user environment, rendering virtual items (e.g., weapons, swords, people), and so forth. Gestures of other objects, limbs, and/or body parts may also be detected and used to render/control the virtual environment. For example, the myelography signals, electroencephalography signals, eye tracking, breathing or breathing, hand movements, etc. may be tracked in real time, whether from the wearer or from another individual in the shared environment. Images captured by

cameras

1108, 1110, 1112, 1114, 1116, 1118 may also be used as contextual inputs. For example, it may be determined that the user is indicating a particular word to be edited or a particular key to be pressed in a word processing application, a particular weapon to be deployed or direction of travel in a game, and so forth.

Further, images captured by the

cameras

1108, 1110, 1112, 1114, 1116, 1118 may be used to implement shared communication or networked interactions in equipment operations, medical training, and/or remote/remote operation guidance applications. A task-specific pose library or neural network machine learning may enable tool identification and feedback on tasks. For example, virtual tools that translate into remote, real actions may be enabled. In yet another example, the HMD system 1100 translates the manipulation of the virtual drill bit within the virtual scene into remote operation of the drill bit on the robotic device deployed for searching for collapsed buildings. Moreover, the HMD system 1100 may be programmable to the extent that it includes a protocol that enables, for example, a user to add a new gesture to a list of identifiable gestures associated with a user action.

Additionally, various cameras in the HMD 1100 may be configurable to detect spectral frequencies outside the visible wavelengths of the spectrum. Multispectral imaging capability in the input camera allows for position tracking of users and/or objects by eliminating unnecessary image features (e.g., background noise). For example, in Augmented Reality (AR) applications such as surgery, instruments and equipment can be tracked by their infrared reflectivity without additional tracking assistance. Also, HMD 1100 may be employed in low visibility situations, where "real-time feeds" from various cameras may be enhanced or enhanced by computer analysis and displayed to the user as visual or audio cues.

The HMD system 1100 can also forego performing any type of data communication with a remote computing system or that requires a power cable (e.g., stand-alone mode of operation). In this regard, the HMD system 1100 may be a "cordless" device having a power unit that allows the HMD system 1100 to operate independently of an external power system. Accordingly, the user may play the full featured game without being tethered to another device (e.g., a game console) or power supply. In the word processing example, HMD system 1100 renders a virtual keyboard and/or a virtual mouse on

displays

1104 and 1106 to provide a virtual desktop or word processing scene. Thus, gesture recognition data captured by one or more of the cameras may represent user typing activity on a virtual keyboard or movement of a virtual mouse. Advantages include, but are not limited to: portability and virtual desktops insulate the privacy of individuals nearby for convenience. The underlying graphics processing architecture may support compression and/or decompression of video and audio signals. Moreover, providing separate images to the left and right eyes of the user may facilitate rendering, generation, and/or perception of the 3D scene. The relative positions of the left-eye display 1104 and the right-eye display 1106 may also be adjustable to match changes in eye separation between different users.

The number of cameras shown in fig. 11 is merely to facilitate discussion. Indeed, depending on the environment, HMD system 1100 may include less than six or more than six cameras.

Functional component of HMD system

Fig. 12 shows the HMD system in more detail. In the example shown, the framework 1102 includes a power unit 1200 (e.g., battery power, adapter) that applies power to the HMD system. The illustrated framework 1102 also includes a motion tracking module 1220 (e.g., accelerometer, gyroscope), wherein the motion tracking module 1220 provides motion tracking data, orientation data, and/or position data to the processor system 1204. The processor system 1204 may include a network adapter 1224 coupled to the I/O bridge 1206. The I/O bridge 1206 may enable communication between the network adapter 1224 and various components such as, for example, an audio input module 1210, an audio output module 1208, a display device 1207, an input camera 1202, and so forth.

In the example shown, audio input module 1210 includes a right audio input 1218 and a left audio input 1216 that detect sounds that may be processed in order to recognize voice commands of the user and nearby individuals. Speech commands recognized in captured audio signals may enhance gesture recognition during modality switching and other applications. Moreover, the captured audio signals may provide 3D information to enhance the immersive experience.

The audio output module 1208 may include a right audio output 1214 and a left audio output 1212. Audio output module 1208 may deliver sound to the ear of the user and/or other nearby individuals. The audio output module 1208 may be in the form of an ear bud, a close-ear speaker, a cover-ear speaker, a loudspeaker, etc., or any combination thereof, and the audio output module 1208 may deliver stereo and/or 3D audio content to the user (e.g., spatial positioning). The illustrated frame 1102 also includes a wireless module 1222, which wireless module 1222 can facilitate communication between the HMD system and various other systems (e.g., computers, wearable devices, game consoles). In one example, the wireless module 1222 communicates with the processor system 1204 via the network adapter 1224.

The display device 1207 shown includes a left-eye display 1104 and a right-eye display 1106, where visual content presented on the

displays

1104, 1106 is available from the processor system 1204 via the I/O bridge 1206. Input cameras 1202 may include left view camera 1116, right view camera 1118, left down view camera 1108, left front view camera 1112, right front view camera 1114, and right down view camera 1110, which have been discussed.

Turning now to fig. 13, a general purpose processing cluster (GPC) 1300 is shown. The illustrated GPC 1300 may be incorporated into a processing system, such as, for example, the processor system 1204 (fig. 12) already discussed. The GPC 1300 may include a pipeline manager 1302 in communication with a scheduler. In one example, pipeline manager 1302 receives tasks from a scheduler and distributes the tasks to one or more Streaming Multiprocessors (SMs) 1304. Each SM 1304 may be configured to process a thread group, where a thread group may be viewed as multiple related threads performing the same or similar operations on different input data. Thus, each thread in the thread group may be assigned to a particular SM 1304. In another example, the number of threads may be greater than the number of execution units in the SM 1304. In this regard, the threads in a thread group may operate in parallel. The pipeline manager 1302 may also assign the processed data destinations to a work distribution crossbar 1308, the work distribution crossbar 1308 in communication with a memory crossbar.

Thus, as each SM 1304 transmits processed tasks to the work distribution crossbar 1308, the processed tasks may be provided to another GPC 1300 for further processing. The output of the SM 1304 may also be sent to a pre-raster operations (preROP) unit 1314, which pre-raster operations unit 1314 in turn directs the data to one or more raster operations units, or performs other operations (e.g., performs address translation, organizes picture color data, mixes colors, etc.). SM 1304 can include an internal level one (L1) cache (not shown) in which SM 1304 can store data. SM 1304 may also have access to a point five level (L1.5) cache 1306 as well as to a level two (L2) cache (not shown) via a Memory Management Unit (MMU) 1310. MMU 1310 may map virtual addresses to physical addresses. In this regard, the MMU 1310 may include Page Table Entries (PTEs) used to map virtual addresses to physical addresses of tiles, memory pages, and/or cache line indices. The illustrated GPU 1300 also includes a texture unit 1312.

Graphics pipeline architecture

Turning now to FIG. 14, a graphics pipeline 1400 is shown. In the example shown, world space pipeline 1420 includes Primitive Distributor (PD) 1402. PD 1402 may collect vertex data associated with higher-order services, graphics primitives, triangles, etc., and communicate the vertex data to a vertex attribute acquisition unit (VAF) 1404. The VAF 1404 may retrieve the vertex attributes associated with each incoming vertex from shared memory and store the vertex data in shared memory along with the associated vertex attributes.

The world space pipeline 1420 shown also includes a vertex, tessellation, geometry processing unit (VTG) 1406. The VTG1406 may include, for example, a vertex processing unit, a tessellation initialization processing unit, a task distributor, a task generation unit, a topology generation unit, a geometry processing unit, a tessellation processing unit, and the like, or any combination thereof. In one example, VTG1406 is a programmable execution unit configured to execute geometry programs, tessellation programs, and vertex shader programs. The programs executed by the VTG1406 may process the vertex data and vertex attributes received from the VAF 1404. Also, programs executed by VTG1406 may generate transparency values, surface normalization factors, graphics primitives, and color values for each vertex of a graphics primitive for further processing within graphics processing pipeline 1400.

The vertex processing units of VTG1406 may be programmable execution units that execute vertex shader programs, such as lighting and transform vertex data as specified by the vertex shader programs. For example, the vertex processing unit may be programmed to transform the vertex data from an object-based coordinate representation (e.g., object space) to an alternative base coordinate system (alternative based coordinated system) such as world space or Normalized Device Coordinate (NDC) space. Further, the vertex processing unit may read the vertex data and vertex attributes stored in the shared memory by the VAF 1404 and process the vertex data and vertex attributes. In one example, the vertex processing unit stores the processed vertices in a shared memory.

A tessellation initialization processing unit (e.g., hull shader, tessellation control shader) may execute a tessellation initialization shader program. In one example, a tessellation initialization processing unit processes vertices produced by a vertex processing unit and generates graphics primitives sometimes referred to as "patches". The tessellation initialization processing unit may also generate various patch attributes, where the patch data and patch attributes are stored in the shared memory. The task generation unit of VTG1406 may retrieve data and attributes for the vertices and patches from shared memory. In one example, the task generation unit generates tasks for processing vertices and patches for processing by later stages in the graphics processing pipeline 1400.

The tasks produced by the task generation unit may be redistributed by a task distributor of the VTG 1406. For example, the tasks produced by the various instances of the vertex shader program and the tessellation initializer may vary significantly between one graphics processing pipeline 1400 and another. Accordingly, the task distributor may redistribute the tasks such that each graphics processing pipeline 1400 has approximately the same workload during later pipeline stages.

As already noted, the VTG1406 may also include a topology generation unit. In one example, the topology generation unit retrieves tasks distributed by the task distributor, indexes vertices including vertices associated with the patches, and calculates an index for forming graphics primitive connection tessellation vertices and coordinates (UV) of the tessellation vertices. The indexed vertices may be stored in the shared memory by the topology generation unit. The tessellation processing unit of VTG1406 may be configured to execute tessellation shader programs (e.g., domain shader, tessellation evaluation shader). The tessellation processing unit may read input data from the shared memory and write output data to the shared memory. The output data may be passed from the shared memory to a geometry processing unit (e.g., the next shader stage) as input data.

The geometry processing units of VTG1406 may execute geometry shader programs to transform graphics primitives (e.g., triangles, line segments, points, etc.). In one example, the vertices are grouped to construct a graphics primitive, where the geometry processing unit subdivides the graphics primitive into one or more new graphics primitives. The geometry processing unit may also operate parameters that may be used to rasterize the new graphics primitive, such as, for example, plane equation coefficients (plane equations).

World space pipeline 1420 shown also includes a viewport scale, culling, and clipping unit (VPC) 1408 that receives parameters and vertices from VTG1406 that specify new graphics primitives. In one example, VPC 1408 performs clipping, flanging (cuffing), perspective correction, and viewport transformation to identify potentially viewable graphics primitives in the final rendered image. VPC 1408 can also identify graphics primitives that may not be viewable.

Graphics processing pipeline 1400 may also include tile unit 1410 coupled to world space pipeline 1420. Tile unit 1410 may be a graphics primitive sorting engine, where graphics primitives are processed in world space pipeline 1420 and then passed to tile unit 1410. In this regard, the graphics processing pipeline 1400 may also include a screen space pipeline 1422, where the screen space may be divided into cache tiles. Each cache tile may thus be associated with a portion of screen space. For each graphics primitive, tile unit 1410 may identify a set of cache tiles (e.g., "tiles") that intersect the graphics primitive. After chunking the plurality of graphics primitives, chunking unit 1410 may process the graphics primitives on a tile-caching basis. In one example, graphics primitives associated with a particular cache tile are communicated, one tile at a time, to setup unit 1412 in screen space pipeline 1422. Graphics primitives that intersect multiple cache tiles may be processed once in world space pipeline 1420 while being passed to screen space pipeline 1422 multiple times.

In one example, setup unit 1412 receives vertex data from VPC 1408 via tile unit 1410 and computes parameters associated with the graphics primitives. The parameters may include, for example, edge equations, plane-of-deviation equations, and depth plane equations. The screen space pipeline 1422 may also include a rasterizer 1414 coupled to the setup unit 1412. The rasterizer may scan convert new graphics primitives and pass the fragments and overlay data to a pixel shading unit (PS) 1416. Rasterizer 1414 may also perform Z culling and other Z-based optimizations.

PS1416, which may access the shared memory, may execute a fragment shader program that transforms fragments received from rasterizer 1414. More specifically, the fragment shader program may color fragments (e.g., work as a pixel shader program) at a pixel level granularity. In another example, a fragment shader program colors fragments at a sample level granularity, where each pixel includes multiple samples, and each sample represents a portion of a pixel. Also, depending on the circumstances (e.g., sampling rate), the fragment shader program may color the fragments at any other granularity. PS1416 may perform blending, shading, perspective correction, texture mapping, etc. to generate shaded segments.

The illustrated screen space pipeline 1422 also includes a raster operations unit (ROP) 1418, which may perform operations such as, for example, stencil printing, Z testing, blending, and the like. ROP 1418 may then transmit the pixel data as processed graphics data to one or more rendered targets (e.g., graphics memory). ROP 1418 may be configured to compress Z or color data written to memory and decompress Z or color data read from memory. The location of the ROP 1418 may vary depending on the environment.

Graphics processing pipeline 1400 may be implemented by one or more processing elements. For example, VTG1406 and/or PS1416 may be implemented in one or more SMs, PD 1402, VAF 1404, VPC 1408, tile unit 1410, setup unit 1412, rasterizer 1414, and/or ROP 1418 may be implemented in a particular GPC processing element along with a corresponding partition unit. Graphics processing pipeline 1400 may also be implemented in fixed functionality hardware logic. In fact, graphics processing pipeline 1400 may be implemented in a PPU.

Thus, the illustrated world space pipeline 1420 processes graphical objects in 3D space, where the position of each graphical object is known relative to other graphical objects and relative to a 3D coordinate system. In contrast, screen space pipeline 1422 may process graphical objects that have been projected from a 3D coordinate system onto a 2D planar surface representing the surface of a display device. Further, the world space pipeline 1420 may be divided into an alpha stage pipeline and a beta stage pipeline, where the alpha stage pipeline includes pipeline stages from the PD 1402 to the task generation unit. The beta stage pipeline may include pipeline stages from the topology generation unit up to VPC 1408. In such cases, graphics processing pipeline 1400 may perform a first set of operations (e.g., a single thread, a group of threads, a plurality of groups of threads acting in concert) in the alpha stage pipeline and a second set of operations (e.g., a single thread, a group of threads, a plurality of groups of threads acting in concert) in the beta stage pipeline.

If multiple graphics processing pipelines 1400 are in use, vertex data and vertex attributes associated with a set of graphics objects may be partitioned such that each graphics processing pipeline 1400 has a similar workload throughout the alpha phase. Accordingly, the alpha phase processing may substantially expand the amount of vertex attributes and vertex data such that the amount of vertex attributes and vertex data produced by the task generation unit is significantly greater than the amount of vertex attributes and vertex data processed by the PD 1402 and VAF 1404. Moreover, even when the alpha phase is started with the same number of attributes, task generation units associated with different graphics processing pipelines 1400 may produce vertex data and vertex attributes having different quality levels. In such cases, the task distributor may redistribute the attributes produced by the alpha stage pipeline so that each graphics processing pipeline 1400 has approximately the same workload at the beginning of the beta stage pipeline.

Turning now to fig. 15, a Streaming Multiprocessor (SM) 1500 is shown. The illustrated SM 1500 includes K scheduler units 1504 coupled to an instruction cache 1502, where each scheduler unit 1504 receives an array of thread blocks from a pipeline manager (not shown) and manages the scheduling of instructions to one or more thread blocks in each active thread block array. The scheduler unit 1504 may schedule threads for execution in parallel thread groups, where each group may be referred to as a "thread bundle (warp)". Thus, each bundle may include, for example, sixty-four threads. In addition, the scheduler unit 1504 may manage a number of different thread blocks, which are assigned to a thread bundle for execution. The scheduler unit may then schedule instructions from a plurality of different thread bundles on various functional units during each clock cycle. Each scheduler unit 1504 may include one or more instruction dispatch units 1522, where each dispatch unit 1522 transfers instructions to one or more of the functional units. The number of dispatch units 1522 may vary depending on the circumstances. In the example shown, scheduler unit 1504 includes two dispatch units 1522 that enable two different instructions from the same thread bundle to be dispatched during each clock cycle.

SM 1500 may also include a register file 1506. Register file 1506 may include a set of registers that are divided among the functional units such that each functional unit is assigned to a dedicated portion of register file 1506. The register file 1506 can also divide between different thread bundles being executed by the SM 1500. In one example, register file 1506 provides temporary storage for operands connected to the data path of the functional unit. The illustrated SM 1500 also includes L processing cores 1508, where L may be a relatively large number (e.g., 192). Each core 1508 may be a pipelined, single precision processing unit that includes a floating point arithmetic logic unit (e.g., IEEE 754-.

The illustrated SM 1500 also includes M Double Precision Units (DPUs) 1510, N Special Function Units (SFUs) 1512, and P load/store units (LSUs) 1514. Each DPU 1510 can implement double precision floating point arithmetic and each SFU 1512 can perform special functions such as rectangular copy pixel blending, for example. Further, each LSU 1514 may implement load and store operations between shared memory 1518 and register file 1506. In one example, load and store operations are implemented through J texture Unit/L1 cache 1520 and interconnection network 1516. In one example, the J texture unit/L1 caches 1520 are also coupled to a crossbar (not shown). Thus, the interconnection network 1516 may connect each of the functional units to the register file 1506 and to the shared memory 1518. In one example, interconnect network 1516 functions as a crossbar that connects any of the functional units to any of the registers in register file 1506.

SM 1500 may be implemented within a graphics processor (e.g., a graphics processing unit/GPU) where texture unit/L1 cache 1520 may access a texture map from memory and sample the texture map to produce sampled texture values for use in shader programs. Texture operations performed by the texture unit/L1 cache 1520 include, but are not limited to, MIP map (mipmap) based antialiasing.

Additional System overview examples

Fig. 16 is a block diagram of a processing system 1600 according to an embodiment. In various embodiments, system 1600 includes one or more processors 1602 and one or more graphics processors 1608, and may be a single-processor desktop system, a multi-processor workstation system, or a server system having a large number of processors 1602 or processor cores 1607. In one embodiment, system 1600 is a processing platform incorporated within a system-on-a-chip (SoC) integrated circuit for use in a mobile device, a handheld device, or an embedded device.

Embodiments of system 1600 may include or may be incorporated within the following: server-based gaming platforms, gaming consoles (including gaming and media consoles, mobile gaming consoles, handheld gaming consoles, or online gaming consoles). In some embodiments, system 1600 is a mobile phone, smartphone, tablet computing device, or mobile internet device. Data processing system 1600 may also include, be coupled with, or be integrated within: a wearable device, such as a smart watch wearable device, a smart eyewear (eyewear) device, an augmented reality device, or a virtual reality device. In some embodiments, the data processing system 1600 is a television or set-top box device having one or more processors 1602 and a graphical interface generated by one or more graphics processors 1608.

In some embodiments, one or more processors 1602 each include one or more processor cores 1607 for processing instructions that, when executed, perform operations for system and user software. In some embodiments, each of the one or more processor cores 1607 is configured to process a particular instruction set 1609. In some embodiments, the instruction set 1609 may facilitate Complex Instruction Set Computing (CISC), Reduced Instruction Set Computing (RISC), or computing via Very Long Instruction Words (VLIW). Multiple processor cores 1607 may each process a different instruction set 1609, which may include instructions for facilitating emulation of other instruction sets. Processor core 1607 may also include other processing devices, such as a Digital Signal Processor (DSP).

In some embodiments, the processor 1602 includes a cache memory 1604. Depending on the architecture, processor 1602 may have a single internal cache or multiple levels of internal cache. In some embodiments, cache memory is shared among various components of the processor 1602. In some embodiments, processor 1602 also uses an external cache (e.g., a level 3 (L3) cache or Last Level Cache (LLC)) (not shown), which may be shared among processor cores 1607 using known cache coherency techniques. A register file 1606 is additionally included in the processor 1602, which may include different types of registers (e.g., integer registers, floating point registers, status registers, and instruction pointer registers) for storing different types of data. Some registers may be general purpose registers while other registers may be processor 1602 specific in design.

In some embodiments, the processor 1602 is coupled to a processor bus 1610 to transfer communication signals (such as address, data, or control signals) between the processor 1602 and other components in the system 1600. In one embodiment, system 1600 uses an exemplary 'hub' system architecture, including a memory controller hub 1616 and an input output (I/O) controller hub 1630. A memory controller hub 1616 facilitates communication between the memory devices and other components of the system 1600, while an I/O controller hub (ICH) 1630 provides a connection to I/O devices via a local I/O bus. In one embodiment, the logic of memory controller hub 1616 is integrated within the processor.

Memory device 1620 may be a Dynamic Random Access Memory (DRAM) device, a Static Random Access Memory (SRAM) device, a flash memory device, a phase change memory device, or some other memory device having suitable properties to act as process memory. In one embodiment, the memory device 1620 may operate as system memory for the system 1600 to store data 1622 and instructions 1621 for use when the one or more processors 1602 execute an application or process. The memory controller hub 1616 is also coupled with an optional external graphics processor 1612, which may communicate with one or more graphics processors 1608 in the processors 1602 to perform graphics and media operations.

In some embodiments, the ICH 1630 enables peripherals to be connected to the memory device 1620 and the processor 1602 via a high-speed I/O bus. I/O peripherals include, but are not limited to: an audio controller 1646, a firmware interface 1628, a wireless transceiver 1626 (e.g., Wi-Fi, bluetooth), a data storage device 1624 (e.g., hard drive, flash memory, etc.), and a legacy I/O controller 1640 for coupling legacy (e.g., personal system 2 (PS/2)) devices to the system. One or more Universal Serial Bus (USB) controllers 1642 connect input devices, such as a keyboard and mouse 1644 combination. A network controller 1634 may also be coupled to the ICH 1630. In some embodiments, a high performance network controller (not shown) is coupled to the processor bus 1610. It will be appreciated that the illustrated system 1600 is exemplary and not limiting, as other types of data processing systems configured in a different manner may also be used. For example, I/O controller hub 1630 may be integrated within the one or more processors 1602, or memory controller hub 1616 and I/O controller hub 1630 may be integrated within a discrete external graphics processor, such as external graphics processor 1612.

FIG. 17 is a block diagram of an embodiment of a processor 1700 having one or more processor cores 1702A-1702N, an integrated memory controller 1714, and an integrated graphics processor 1708. Those elements of fig. 17 having the same reference numbers (or names) as the elements of any other figure herein can operate or function in any manner similar to that described elsewhere herein, but are not so limited. Processor 1700 may include additional cores up to and including additional core 1702N, represented by the dashed box. Each of processor cores 1702A-1702N includes one or more internal cache units 1704A-1704N. In some embodiments, each processor core is also capable of accessing one or more shared cache units 1706.

Internal cache units 1704A-1704N and shared cache unit 1706 represent cache memory levels within processor 1700. The cache memory hierarchy may include at least one level of instruction and data cache within each processor core and one or more levels of shared mid-level cache, such as level 2 (L2), level 3 (L3), level 4 (L4), or other levels of cache, with the highest level cache ahead of external memory being categorized as an LLC. In some embodiments, cache coherency logic maintains coherency between the various cache molecules 1706 and 1704A-1704N.

In some embodiments, processor 1700 may also include a set of one or more bus controller units 1716 and a system agent core 1710. The one or more bus controller units 1716 manage a set of peripheral buses, such as one or more peripheral component interconnect buses (e.g., PCI express buses). System agent core 1710 provides management functionality for various processor components. In some embodiments, system agent core 1710 includes one or more integrated memory controllers 1714 to manage access to various external memory devices (not shown).

In some embodiments, one or more of the processor cores 1702A-1702N include support for simultaneous multithreading. In such an embodiment, system proxy core 1710 includes components to coordinate and operate cores 1702A-1702N during multithreaded processing. System agent core 1710 may additionally include a Power Control Unit (PCU) that includes logic and components for regulating the power state of processor cores 1702A-1702N and graphics processor 1708.

In some embodiments, the processor 1700 additionally includes a graphics processor 1708 for performing graphics processing operations. In some embodiments, graphics processor 1708 is coupled to a set of shared cache units 1706 and system agent core 1710 (including one or more integrated memory controllers 1714). In some embodiments, a display controller 1711 is coupled to the graphics processor 1708 to drive graphics processor output to one or more coupled displays. In some embodiments, display controller 1711 may be a separate module coupled with the graphics processor via at least one interconnect, or may be integrated within graphics processor 1708 or system agent core 1710.

In some embodiments, ring-based interconnect unit 1712 is used to couple the internal components of processor 1700. However, alternative interconnection elements may be used, such as point-to-point interconnections, switched interconnections, or other techniques, including those well known in the art. In some embodiments, graphics processor 1708 is coupled to ring interconnect 1712 via I/O link 1713.

The example I/O link 1713 represents at least one of a variety of I/O interconnects, including an on-package I/O interconnect that facilitates communication between various processor components and a high performance embedded memory module 1718, such as an eDRAM module. In some embodiments, each of the processor cores 1702-1702N and the graphics processor 1708 use the embedded memory module 1718 as a shared last level cache.

In some embodiments, processor cores 1702A-1702N are homogeneous cores that execute the same instruction set architecture. In another embodiment, processor cores 1702A-1702N are heterogeneous in Instruction Set Architecture (ISA), in which one or more of processor cores 1702A-N execute a first instruction set and at least one of the other cores executes a subset of the first instruction set or a different instruction set. In one embodiment, processor cores 1702A-1702N are heterogeneous in micro-architecture in that one or more cores having relatively higher power consumption are coupled with one or more power cores having lower power consumption. Additionally, processor 1700 may be implemented on one or more chips or as an SoC integrated circuit having the illustrated components, among other components.

Fig. 18 is a block diagram of a graphics processor 1800, which may be a discrete graphics processing unit, or may be a graphics processor integrated with multiple processing cores. In some embodiments, the graphics processor communicates via a mapped I/O interface to registers on the graphics processor and with commands placed in processor memory. In some embodiments, the graphics processor 1800 includes a memory interface 1814 for accessing memory. Memory interface 1814 may be an interface to local memory, one or more internal caches, one or more shared external caches, and/or to system memory.

In some embodiments, the graphics processor 1800 also includes a display controller 1802 for driving display output data to a display device 1820. Display controller 1802 includes a composition of multiple layers of video or user interface elements and hardware for one or more overlapping planes of the display. In some embodiments, the graphics processor 1800 includes a video codec engine 1806 for encoding, decoding, or transcoding media to, from, or between one or more media encoding formats, including but not limited to: moving Picture Experts Group (MPEG) formats such as MPEG-2, Advanced Video Coding (AVC) formats such as h.264/MPEG-4 AVC, and society of motion picture & television engineers (SMPTE) 421M/VC-1, and Joint Photographic Experts Group (JPEG) formats such as JPEG, and motion JPEG (mjpeg) formats.

In some embodiments, graphics processor 1800 includes a block image transfer (BLIT) engine 1804 to perform two-dimensional (2D) rasterizer operations, including, for example, bit boundary block transfers. However, in one embodiment, 2D graphics operations are performed using one or more components of a Graphics Processing Engine (GPE) 1810. In some embodiments, graphics processing engine 1810 is a computing engine for performing graphics operations, including three-dimensional (3D) graphics operations and media operations.

In some embodiments, the GPE 1810 includes a 3D pipeline 1812 for performing 3D operations, such as rendering three-dimensional images and scenes using processing functions that act on 3D primitive shapes (e.g., rectangles, triangles, etc.). The 3D pipeline 1812 contains programmable and fixed function elements that perform various tasks within the elements and/or generate threads of execution to the 3D/media subsystem 1815. While the 3D pipeline 1812 may be used to perform media operations, embodiments of the GPE 1810 also include a media pipeline 1816 that is specifically used to perform media operations such as video post-processing and image enhancement.

In some embodiments, media pipeline 1816 includes fixed-function or programmable logic units to perform one or more specialized media operations (such as video decoding acceleration, video de-interleaving, and video encoding acceleration) in place of or on behalf of video codec engine 1806. In some embodiments, media pipeline 1816 additionally includes a thread generation unit to generate threads for execution on 3D/media subsystem 1815. The generated threads perform computations for media operations at one or more graphics execution units included in 3D/media subsystem 1815.

In some embodiments, 3D/media subsystem 1815 includes logic to execute threads generated by 3D pipeline 1812 and media pipeline 1816. In one embodiment, the pipeline sends thread execution requests to the 3D/media subsystem 1815, which includes thread dispatch logic to arbitrate and dispatch various requests for available thread execution resources. The execution resources include an array of graphics execution units for processing 3D and media threads. In some embodiments, 3D/media subsystem 1815 includes one or more internal caches for thread instructions and data. In some embodiments, the subsystem further includes shared memory (including registers and addressable memory) to share data between threads and store output data.

3D/media processing

Figure 19 is a block diagram of a graphics processing engine 1910 of a graphics processor according to some embodiments. In one embodiment, GPE 1910 is a version of GPE 1810 shown in fig. 18. Elements in fig. 19 having the same reference numbers (or names) as elements of any other figure herein may operate or function in any manner similar to that described elsewhere herein, but are not so limited.

In some embodiments, GPE 1910 is coupled with a command streamer 1903 that streams commands to GPE 3D and

media pipelines

1912, 1916. In some embodiments, command stream transmitter 1903 is coupled to a memory, which may be a system memory, or may be one or more of an internal cache memory and a shared cache memory. In some embodiments, command streamer 1903 receives commands from memory and sends commands to 3D pipeline 1912 and/or media pipeline 1916. The command is an indication to fetch from a ring buffer that stores commands for the 3D pipeline 1912 and the media pipeline 1916. In one embodiment, the ring buffer may additionally include a batch command buffer that stores a plurality of batches of multiple commands. The 3D pipeline 1912 and the media pipeline 1916 process the commands by performing operations via logic within the respective pipelines or by dispatching one or more threads of execution to the array of execution units 1914. In some embodiments, execution unit array 1914 is scalable such that the array includes a variable number of execution units based on the target power and performance level of GPE 1910.

In some embodiments, the sampling engine 1930 is coupled with a memory (e.g., cache memory or system memory) and an execution unit array 1914. In some embodiments, the sampling engine 1930 provides a memory access mechanism for the execution unit array 1914 that allows the execution array 1914 to read graphics and media data from memory. In some embodiments, the sampling engine 1930 includes logic to perform specialized image sampling operations for media.

In some embodiments, specialized media sampling logic in the sampling engine 1930 includes a de-noising/de-interleaving module 1932, a motion estimation module 1934, and an image scaling and filtering module 1936. In some embodiments, denoising/deinterleaving module 1932 comprises logic to perform one or more of denoising or deinterleaving algorithms on the decoded video data. The de-interlacing logic combines alternating fields of interlaced video content into a single frame of video. The de-noising logic reduces or removes data noise from the video and image data. In some embodiments, the de-noising logic and de-interleaving logic are motion adaptive and use spatial or temporal filtering based on the amount of motion detected in the video data. In some embodiments, the de-noising/de-interleaving module 1932 includes specialized motion detection logic (e.g., within the motion estimation engine 1934).

In some embodiments, the motion estimation engine 1934 provides hardware acceleration of video operations by performing video acceleration functions (such as motion vector estimation and prediction) on the video data. The motion estimation engine determines motion vectors that describe a transformation of image data between successive video frames. In some embodiments, the graphics processor media codec uses video motion estimation engine 1934 to perform operations on macroblock-level video that may otherwise be too computationally intensive to perform with a general purpose processor. In some embodiments, the motion estimation engine 1934 may be generally available to a graphics processor component in order to assist video decoding and processing functions that are sensitive or adaptive to the direction or magnitude of motion within the video data.

In some embodiments, the image scaling and filtering module 1936 performs image processing operations to enhance the visual quality of the resulting images and video. In some embodiments, the scaling and filtering module 1936 processes image and video data during a sampling operation before providing the data to the execution unit array 1914.

In some embodiments, GPE 1910 includes a data port 1944, which provides an additional mechanism for the graphics subsystem to access memory. In some embodiments, data port 1944 facilitates memory access for operations including render-target writes, constant buffer reads, scratch memory space reads/writes, and media surface (media surface) accesses. In some embodiments, data port 1944 includes cache memory space for caching access to memory. The cache memory may be a single data cache, or multiple caches separated into multiple subsystems for accessing memory via the data port (e.g., a render buffer cache, a constant buffer cache, etc.). In some embodiments, threads executing on execution units in execution unit array 1914 communicate with data ports by exchanging messages via a data distribution interconnect that couples each subsystem of GPE 1910.

Execution unit

Fig. 20 is a block diagram of another embodiment of a graphics processor 2000. Elements in fig. 20 having the same reference numbers (or names) as elements of any other figure herein may operate or function in any manner similar to that described elsewhere herein, but are not so limited.

In some embodiments, graphics processor 2000 includes a ring interconnect 2002, a pipeline front end 2004, a media engine 2037, and graphics cores 2080A-2080N. In some embodiments, ring interconnect 2002 couples the graphics processor to other processing units, including other graphics processors or one or more general purpose processor cores. In some embodiments, the graphics processor is one of many processors integrated within a multi-core processing system.

In some embodiments, graphics processor 2000 receives multiple batches of commands via ring interconnect 2002. Incoming commands are interpreted by a command streamer 2003 in the pipeline front end 2004. In some embodiments, graphics processor 2000 includes scalable execution logic to perform 3D geometry processing and media processing via graphics cores 2080A-2080N. For 3D geometry processing commands, command stream transmitter 2003 supplies the commands to geometry pipeline 2036. For at least some media processing commands, the command streamer 2003 supplies the commands to a video front end 2034, which is coupled to a media engine 2037. In some embodiments, the media engine 2037 includes a Video Quality Engine (VQE) 2030 for video and image post-processing and a multi-format encode/decode (MFX) 2033 engine for providing hardware accelerated media data encoding and decoding. In some embodiments, geometry pipeline 2036 and media engine 2037 each generate a thread of execution for thread execution resources provided by at least one graphics core 2080A.

In some embodiments, graphics processor 2000 includes scalable thread execution resources featuring modular cores 2080A-2080N (sometimes referred to as core slices), each modular core having multiple sub-cores 2050A-2050N, 2060A-2060N (sometimes referred to as core slices). In some embodiments, graphics processor 2000 may have any number of graphics cores 2080A to 2080N. In some embodiments, graphics processor 2000 includes a graphics core 2080A having at least a first sub-core 2050A and a second sub-core 2060A. In other embodiments, the graphics processor is a low power processor with a single subcore (e.g., 2050A). In some embodiments, the graphics processor 2000 includes a plurality of graphics cores 2080A-2080N, each including a set of first sub-cores 2050A-2050N and a set of second sub-cores 2060A-2060N. Each sub-core of the set of first sub-cores 2050A-2050N includes at least a first set of execution units 2052A-2052N and media/texture samplers 2054A-2054N. Each sub-core of the set of second sub-cores 2060A-2060N includes at least a second set of execution units 2062A-2062N and samplers 2064A-2064N. In some embodiments, each of the sub-cores 2050A-2050N, 2060A-2060N shares a set of shared resources 2070A-2070N. In some embodiments, these shared resources include shared cache memory and pixel operation logic. Other shared resources may also be included in various embodiments of the graphics processor.

FIG. 21 illustrates thread execution logic 2100, comprising an array of processing elements employed in some embodiments of a GPE. Those elements of fig. 21 having the same reference numbers (or names) as the elements of any other figure herein can operate or function in any manner similar to that described elsewhere herein, but are not so limited.

In some embodiments, thread execution logic 2100 includes a pixel shader 2102, a thread dispatcher 2104, an instruction cache 2106, a scalable array of execution units (including multiple execution units 2108A-2108N), a sampler 2110, a data cache 2112, and a data port 2114. In one embodiment, these included components are interconnected via an interconnect fabric that links to each of these components. In some embodiments, thread execution logic 2100 includes one or more connections to memory (such as system memory or cache memory) through one or more of instruction cache 2106, data port 2114, sampler 2110, and execution unit arrays 2108A-2108N. In some embodiments, each execution unit (e.g., 2108A) is a separate vector processor capable of executing multiple simultaneous threads and processing multiple data elements in parallel for each thread. In some embodiments, the execution unit arrays 2108A-2108N include any number of individual execution units.

In some embodiments, the EU arrays 2108A-2108N are used primarily to execute "shader" programs. In some embodiments, execution units in arrays 2108A-2108N execute instruction sets that include native support for many standard 3D graphics shader instructions, such that shader programs from graphics libraries (e.g., Direct3D and OpenGL) are executed with minimal translation. Execution units support vertex and geometry processing (e.g., vertex programs, geometry programs, vertex shaders), pixel processing (e.g., pixel shaders, fragment shaders), and general purpose processing (e.g., compute and media shaders).

Each execution unit of the array of execution units 2108A-2108N operates on an array of data elements. The number of data elements is the "execution size" or number of lanes for the instruction. An execution channel is a logical unit for flow control, data element access, and execution of masking within an instruction. The number of channels may be independent of the number of physical Arithmetic Logic Units (ALUs) or Floating Point Units (FPUs) for a particular graphics processor. In some embodiments, execution units 2108A-2108N support both integer and floating point data types.

The execution unit instruction set includes Single Instruction Multiple Data (SIMD) instructions. Various data elements may be stored as packed data types in registers, and the execution unit will process the various elements based on the data size of the elements. For example, when operating on a 256-bit wide vector, the 256-bit vector is stored in a register, and the execution unit operates on the vector as four separate 64-bit packed data elements (data elements of a Quadword (QW) size), eight separate 32-bit packed data elements (data elements of a double word length (DW) size), sixteen separate 16-bit packed data elements (data elements of a word length (W) size), or thirty-two separate 8-bit data elements (data elements of a byte (B) size). However, different vector widths and register sizes are possible.

One or more internal instruction caches (e.g., 2106) are included in thread execution logic 2100 to cache thread instructions for execution units. In some embodiments, one or more data caches (e.g., 2112) are included for caching thread data during thread execution. In some embodiments, sampler 2110 is included for providing texture samples for 3D operations and media samples for media operations. In some embodiments, sampler 2110 includes specialized texture or media sampling functionality to process texture or media data during the sampling process prior to providing the sampled data to the execution unit.

During execution, the graphics pipeline and the media pipeline send thread initiation requests to the thread execution logic 2100 via the thread generation and dispatch logic. In some embodiments, thread execution logic 2100 includes a native thread dispatcher 2104 that arbitrates thread initiation requests from the graphics pipeline and the media pipeline and instantiates the requested thread on one or more execution units 2108A-2108N. For example, a geometry pipeline (e.g., 2036 of FIG. 20) dispatches vertex processing, tessellation, or geometry processing threads to thread execution logic 2100 (FIG. 21). In some embodiments, thread dispatcher 2104 may also process runtime thread generation requests from executing shader programs.

Once the group of geometric objects has been processed and rasterized into pixel data, the pixel shader 2102 is invoked to further compute output information and cause the results to be written to an output surface (e.g., a color buffer, a depth buffer, a stencil buffer, etc.). In some embodiments, pixel shader 2102 computes values for various vertex attributes that are interpolated across rasterized objects. In some embodiments, pixel shader 2102 then executes an Application Programming Interface (API) supplied pixel shader program. To execute the pixel shader program, the pixel shader 2102 dispatches threads to an execution unit (e.g., 2108A) via a thread dispatcher 2104. In some embodiments, pixel shader 2102 uses texture sampling logic in sampler 2110 to access texture data in a texture map stored in memory. Arithmetic operations on the texture data and the input geometry data calculate pixel color data for each geometric segment, or discard one or more pixels as further processed.

In some embodiments, the data port 2114 provides a memory access mechanism for the thread execution logic 2100 to output processed data to memory for processing on a graphics processor output pipeline. In some embodiments, the data port 2114 includes or is coupled to one or more cache memories (e.g., data cache 2112) to cache data for memory access via the data port.

Fig. 22 is a block diagram illustrating a graphics processor instruction format 2200 in accordance with some embodiments. In one or more embodiments, a graphics processor execution unit supports an instruction set having instructions in multiple formats. The solid line boxes show components that are typically included in an execution unit instruction, while the dashed lines include components that are optional or included only in a subset of instructions. In some embodiments, the instruction format 2200 described and illustrated is macro-instructions in that they are instructions supplied to the execution units, as opposed to micro-operations that result from instruction decoding (once the instructions are processed).

In some embodiments, the graphics processor execution unit native supports instructions in 128-bit format 2210. A 64-bit compact instruction format 2230 is available for some instructions based on the selected instruction, instruction options, and number of operands. Native 128-bit format 2210 provides access to all instruction options, while some options and operations are restricted to 64-bit format 2230. The native instructions available in the 64-bit format 2230 vary depending on the embodiment. In some embodiments, the instruction is partially compacted using a set of index values in index field 2213. The execution unit hardware references a set of compact tables based on the index values and uses the compact table outputs to reconstruct the native instructions in a 128-bit format 2210.

For each format, instruction opcode 2212 defines the operation to be performed by the execution unit. An execution unit executes each instruction in parallel across multiple data elements of each operand. For example, in response to an add instruction, the execution unit performs a simultaneous add operation across each color channel representing a texel or a picture element. By default, the execution unit executes each instruction across all data lanes of operands. In some embodiments, the instruction control field 2214 enables control over certain execution options, such as channel selection (e.g., prediction) and data channel ordering (e.g., swizzle). for the 128-bit instruction 2210, the execution size field 2216 limits the number of data channels to be executed in parallel.

Some execution unit instructions have up to three operands, including two source operands, src 02220, src12222, and one destination 2218. In some embodiments, the execution unit supports dual destination instructions, where one of these destinations is implicit. The data manipulation instruction may have a third source operand (e.g., SRC 22224), where the instruction opcode 2212 determines the number of source operands. The last source operand of an instruction may be an immediate (e.g., hard-coded) value passed through the instruction.

In some embodiments, 128-bit instruction format 2210 includes access/addressing mode information 2226 that specifies whether a direct register addressing mode or an indirect register addressing mode is used, for example. When the direct register addressing mode is used, the register addresses of one or more operands are provided directly by bits in instruction 2210.

In some embodiments, 128-bit instruction format 2210 includes an access/addressing mode field 2226 that specifies an addressing mode and/or an access mode for the instruction. In one embodiment, the access pattern is used to define a data access alignment for the instruction. Some embodiments support access patterns that include 16 byte aligned access patterns and 1 byte aligned access patterns, where the byte alignment of the access patterns determines the access alignment of instruction operands. For example, when in the first mode, instruction 2210 may use byte-aligned addressing for source operands and destination operands, and when in the second mode, instruction 2210 may use 16 byte-aligned addressing for all source operands and destination operands.

In one embodiment, the addressing mode portion of access/addressing mode field 2226 determines whether the instruction will use direct addressing or indirect addressing. When using the direct register addressing mode, bits in instruction 2210 directly provide the register address of one or more operands. When an indirect register addressing mode is used, register addresses for one or more operands may be calculated based on an address immediate field and an address register value in the instruction.

In some embodiments, instructions are grouped based on opcode 2212 bit fields to simplify opcode decoding 2240. For an 8-bit opcode,

bits

4, 5, and 6 allow the execution unit to determine the type of opcode. The exact operation code groupings shown are examples only. In some embodiments, move and logical opcode group 2242 includes data move and logical instructions (e.g., move (mov), compare (cmp)). In some embodiments, move and logical group 2242 shares the five Most Significant Bits (MSBs), with a move (mov) instruction in the form 0000 xxxxxxb and a logical instruction in the form 0001 xxxxb. Flow control instruction group 2244 (e.g., call, jump (jmp)) includes instructions in the form 0010 xxxxxxx (e.g., 0x 20). Miscellaneous instruction group 2246 includes a mixture of instructions including synchronous instructions (e.g., wait, send) in the form of 0011 xxxxxxb (e.g., 0x 30). Parallel math instruction group 2248 includes component-by-component arithmetic instructions (e.g., add, multiply (mul)) in the form 0100 xxxxx (e.g., 0x 40). The parallel math group 2248 performs arithmetic operations in parallel across data lanes. Vector math group 2250 includes arithmetic instructions (e.g., dp 4) in the form 0101xxxxb (e.g., 0x 50). The vector math group performs arithmetic such as dot product (dot production) calculations on vector operands.

Graphics pipeline

Fig. 23 is a block diagram of another embodiment of a graphics processor 2300. Elements in fig. 23 having the same reference numbers (or names) as elements of any other figure herein can operate or function in any manner similar to that described elsewhere herein, but are not so limited.

In some embodiments, graphics processor 2300 includes graphics pipeline 2320, media pipeline 2330, display engine 2340, thread execution logic 2350, and rendering output pipeline 2370. In some embodiments, graphics processor 2300 is a graphics processor within a multi-core processing system that includes one or more general purpose processing cores. Graphics processor is controlled by register writes to one or more control registers (not shown) or via commands issued to graphics processor 2300 via ring interconnect 2302. In some embodiments, ring interconnect 2302 couples graphics processor 2300 to other processing components, such as other graphics processors or general purpose processors. Commands from ring interconnect 2302 are interpreted by command streamer 2303, which supplies instructions to separate components of graphics pipeline 2320 or media pipeline 2330.

In some embodiments, command streamer 2303 directs the operation of vertex fetcher 2305, which reads vertex data from memory and executes vertex processing commands provided by command streamer 2303. In some embodiments, vertex fetcher 2305 provides vertex data to vertex shaders 2307, which perform coordinate space transformations and lighting operations on each vertex. In some embodiments, vertex fetcher 2305 and vertex shader 2307 execute vertex processing instructions by dispatching execution threads to execution units 2352A, 2352B via thread dispatcher 2331.

In some embodiments, the execution units 2352A, 2352B are an array of vector processors having instruction sets for performing graphics and media operations. In some embodiments, the execution units 2352A, 2352B have an L1 cache 2351 specific to each array or attachment shared between arrays. The cache may be configured as a data cache, an instruction cache, or a single cache that is partitioned to contain data and instructions in different partitions.

In some embodiments, graphics pipeline 2320 includes a tessellation component to perform hardware accelerated tessellation of 3D objects. In some embodiments, the programmable hull shader 2311 configures tessellation operations. The programmable domain shader 2317 provides back-end evaluation of the tessellation output. The tessellator 2313 operates in the direction of the hull shader 2311 and contains special logic for generating a detailed set of geometric objects based on a coarse geometry model that is provided as input to the graphics pipeline 2320. In some embodiments, if no tessellation is used, the

tessellation components

2311, 2313, 2317 may be bypassed.

In some embodiments, a complete geometric object may be processed by geometry shader 2319 via one or more threads dispatched to execution units 2352A, 2352B, or may proceed directly to clipper 2329. In some embodiments, the geometry shader operates on the entire geometry object (rather than patches or vertices as vertices in a previous stage of the graphics pipeline). If tessellation is disabled, the geometry shader 2319 receives input from the vertex shader 2307. In some embodiments, if the tessellation unit is disabled, the geometry shader 2319 may be programmed by a geometry shader program to perform geometry tessellation.

Prior to rasterization, clipper 2329 processes the vertex data. Clipper 2329 may be a fixed-function clipper or a programmable clipper with clipping and geometry shader functionality. In some embodiments, a rasterizer 2373 (e.g., a depth test component) in the render output pipeline 2370 dispatches pixel shaders to convert geometric objects into their per-pixel representations. In some embodiments, pixel shader logic is included in thread execution logic 2350. In some embodiments, the application may bypass the rasterizer 2373 and access the un-rasterized vertex data via a streaming out unit (streaming out unit) 2323.

Graphics processor 2300 has an interconnect bus, interconnect fabric, or some other interconnect mechanism that allows data and messages to be passed among the main components of the processor. In some embodiments, execution units 2352A, 2352B and associated cache(s) 2351, texture and media sampler 2354, and texture/sampler cache 2358 are interconnected via data port 2356 to perform memory accesses and communicate with the rendering output pipeline components of the processor. In some embodiments, sampler 2354,

caches

2351, 2358, and execution units 2352A, 2352B each have separate memory access paths.

In some embodiments, the rendering output pipeline 2370 includes a rasterizer 2373 that converts vertex-based objects into associated pixel-based representations. In some embodiments, the rasterizer logic includes a windower (window)/masker unit for performing fixed-function triangle and line rasterization. An associated render cache 2378 and depth cache 2379 may also be available in some embodiments. The pixel operations component 2377 performs pixel-based operations on the data, although in some examples, pixel operations associated with 2D operations (e.g., bit block images are transmitted with blending) are performed by the 2D engine 2341 or replaced at display time by the display controller 2343 using overlapping display planes. In some embodiments, a shared L3 cache 2375 may be available for all graphics components, allowing data to be shared without the use of main system memory.

In some embodiments, graphics processor media pipeline 2330 includes a media engine 2337 and a video front end 2334. In some embodiments, video front end 2334 receives pipelined commands from command streamer 2303. In some embodiments, media pipeline 2330 includes a separate command streamer. In some embodiments, video front end 2334 processes the media commands before sending the commands to media engine 2337. In some embodiments, media engine 2337 includes thread generation functionality for generating threads for dispatch to thread execution logic 2350 via thread dispatcher 2331.

In some embodiments, graphics processor 2300 includes a display engine 2340. In some embodiments, display engine 2340 is external to processor 2300 and is coupled with the graphics processor via ring interconnect 2302, or some other interconnect bus or fabric. In some embodiments, the display engine 2340 includes a 2D engine 2341 and a display controller 2343. In some embodiments, the display engine 2340 includes dedicated logic capable of operating independently of the 3D pipeline. In some embodiments, the display controller 2343 is coupled with a display device (not shown), which may be a system-integrated display device (as in a laptop computer), or may be an external display device attached via a display device connector.

In some embodiments, graphics pipeline 2320 and media pipeline 2330 may be configured to perform operations based on multiple graphics and media programming interfaces and are not specific to any one Application Programming Interface (API). In some embodiments, driver software for the graphics processor translates API calls specific to a particular graphics or media library into commands that can be processed by the graphics processor. In some embodiments, support is provided for the open graphics library (OpenGL) and open computing language (OpenCL) from the kornas Group (Khronos Group), the Direct3D library from microsoft corporation, or support may be provided for both OpenGL and D3D. Support may also be provided for an open source computer vision library (OpenCV). Future APIs with compatible 3D pipelines will also be supported if a mapping from the pipeline of the future API to the pipeline of the graphics processor can be made.

Graphics pipeline programming

Figure 24A is a block diagram of a graphics processor command format 2400 according to some embodiments. Fig. 24B is a block diagram of a graphics processor command sequence 2410, according to an embodiment. The solid line boxes in FIG. 24A show components that are typically included in graphics commands, while the dashed lines include components that are optional or included only in a subset of graphics commands. The exemplary graphics processor command format 2400 of FIG. 24A includes data fields for identifying the target client 2402 for the command, a command operation code (opcode) 2404, and associated data 2406 for the command. Also included in some commands are a sub-opcode 2405 and a command size 2408.

In some embodiments, client 2402 specifies a client unit of the graphics device that processes command data. In some embodiments, the graphics processor command parser examines the client field of each command to coordinate further processing of the command and to route the command data to the appropriate client unit. In some embodiments, a graphics processor client unit includes a memory interface unit, a rendering unit, a 2D unit, a 3D unit, and a media unit. Each client unit has a corresponding processing pipeline that processes commands. Once the command is received by the client unit, the client unit reads the opcode 2404 and, if present, the sub-opcode 2405 to determine the operation to be used for execution. The client unit uses the information in data field 2406 to execute the command. For some commands, an explicit command size 2408 is expected to specify the size of the command. In some embodiments, the command parser automatically determines the size of at least some of the commands based on the command opcode. In some embodiments, the commands are aligned via multiples of double word length.

An exemplary graphics processor command sequence 2410 is shown in the flow diagram of fig. 24B. In some embodiments, software or firmware of a data processing system featuring an embodiment of a graphics processor uses the illustrated version of the command sequence to set up, execute, and terminate a set of graphics operations. Sample command sequences are shown and described for purposes of example only, as embodiments are not limited to these particular commands or this sequence of commands. Further, the commands may be issued as a batch of commands in a command sequence such that the graphics processor will process the command sequence in an at least partially simultaneous manner.

In some embodiments, graphics processor command sequence 2410 may begin with a pipeline flush command 2412 to cause any active graphics pipelines to complete the currently pending commands for the pipelines. In some embodiments, the 3D pipeline 2422 and the media pipeline 2424 do not operate at the same time. A pipeline flush is performed to cause the active graphics pipeline to complete any pending commands. In response to a pipeline flush, a command parser for a graphics processor will halt command processing until the active drawing engine completes pending operations and the associated read cache is invalidated. Alternatively, any data in the render cache marked 'dirty' may be flushed to memory. In some embodiments, the pipeline flush command 2412 may be used for pipeline synchronization or before placing the graphics processor in a low power state.

In some embodiments, the pipeline select command 2413 is used when the command sequence requires the graphics processor to explicitly switch between pipelines. In some embodiments, the pipeline select command 2413 is required only once within the execution context before issuing the pipeline command, unless the context is to issue commands for both pipelines. In some embodiments, pipeline flush command 2412 is required immediately prior to pipeline switch via pipeline select command 2413.

In some embodiments, pipeline control commands 2414 configure the graphics pipeline for operation and for programming 3D pipeline 2422 and media pipeline 2424. In some embodiments, the pipeline control commands 2414 configure the pipeline state for the active pipeline. In one embodiment, the pipeline control commands 2414 are used for pipeline synchronization and for flushing data from one or more cache memories within the active pipeline before processing a batch of commands.

In some embodiments, a set of return buffers for a respective pipeline to write data is configured using return buffer status commands 2416. Some pipelining operations require allocation, selection, or configuration of one or more return buffers into which the operations write intermediate data during processing. In some embodiments, the graphics processor also uses one or more return buffers to store output data and perform cross-thread communications. In some embodiments, the return buffer status 2416 includes selecting a size and number of return buffers to use for the set of pipelined operations.

The remaining commands in the command sequence differ based on the active pipeline for the operation. Based on the pipeline determination 2420, the command sequence is customized for the 3D pipeline 2422 or the media pipeline 2424, the 3D pipeline starting at the 3D pipeline state 2430, the media pipeline starting at the media pipeline state 2440.

The commands for 3D pipeline state 2430 include 3D state set commands for: vertex buffer state, vertex element state, constant color state, depth buffer state, and other state variables to be configured prior to processing the 3D primitive command. The values of these commands are determined based at least in part on the particular 3D API in use. In some embodiments, the 3D pipeline state 2430 command can also selectively disable or bypass certain pipeline elements (if those elements are not to be used).

In some embodiments, the 3D primitive 2432 command is for submitting a 3D primitive for processing by the 3D pipeline. Commands and associated parameters passed to the graphics processor via 3D primitive 2432 are forwarded to a vertex fetch function in the graphics pipeline. The vertex fetch function uses the 3D primitive 2432 command data to generate a vertex data structure. The vertex data structure is stored in one or more return buffers. In some embodiments, the 3D primitive 2432 commands are for performing vertex operations on 3D primitives via a vertex shader. To process the vertex shader, 3D pipeline 2422 dispatches shader execution threads to the graphics processor execution unit.

In some embodiments, 3D pipeline 2422 is triggered via an execute 2434 command or event. In some embodiments, the register write triggers the command execution. In some embodiments, execution is triggered via a 'go (go)' or 'kick (kick)' command in a command sequence. In one embodiment, a pipeline synchronization command is used to trigger command execution to flush a sequence of commands through a graphics pipeline. The 3D pipeline will perform geometric processing for the 3D primitives. Once the operation is complete, the resulting geometric object is rasterized and the pixel engine colors the resulting pixels. Additional commands for controlling pixel shading and pixel back-end operations may also be included for those operations.

In some embodiments, graphics processor command sequence 2410 follows the media pipeline 2424 path when performing media operations. In general, the manner and particular use of programming for media pipeline 2424 depends on the media or computing operation to be performed. During media decoding, certain media decoding operations may be offloaded to the media pipeline. In some embodiments, the media pipeline may also be bypassed and media decoding may be performed in whole or in part (using resources provided by one or more general purpose processing cores). In one embodiment, the media pipeline further comprises elements for General Purpose Graphics Processor Unit (GPGPU) operations, wherein the graphics processor is to perform SIMD vector operations using a compute shader program that is not explicitly related to the rendering of graphics primitives.

In some embodiments, media pipeline 2424 is configured in a similar manner as 3D pipeline 2422. A set of media pipeline state commands 2440 are dispatched or placed into a command queue before media object commands 2442. In some embodiments, the media pipeline status command 2440 includes data for configuring the media pipeline element that will be used to process the media object. This includes data (such as encoding or decoding formats) for configuring video decoding and video encoding logic within the media pipeline. In some embodiments, media pipeline state command 2440 also supports the use of one or more pointers to "indirect" state elements containing a collection of state settings.

In some embodiments, media object command 2442 supplies a pointer to the media object for processing by the media pipeline. The media object includes a memory buffer containing video data to be processed. In some embodiments, all of the media pipeline state must be valid before issuing the media object command 2442. Once the pipeline state is configured and the media object command 2442 is queued, the media pipeline 2424 is triggered via an execute command 2444 or equivalent execute event (e.g., a register write). The output from the media pipeline 2424 may then be post-processed by operations provided by the 3D pipeline 2422 or the media pipeline 2424. In some embodiments, GPGPU operations are configured and performed in a similar manner as media operations.

Graphics software architecture

FIG. 25 illustrates an exemplary graphical software architecture for a data processing system 2500 according to some embodiments. In some embodiments, the software architecture includes a 3D graphics application 2510, an operating system 2520, and at least one processor 2530. In some embodiments, the processors 2530 include a graphics processor 2532 and one or more general purpose processor cores 2534. Graphics application 2510 and operating system 2520 each execute in data processing system memory 2550.

In some embodiments, 3D graphics application 2510 includes one or more shader programs, including shader instructions 2512. The shader language instructions can be in a high-level shader language, such as high-level shader language (HLSL) or OpenGL shader language (GLSL). The application also includes executable instructions 2514 in a machine language suitable for execution by the general purpose processor core 2534. The application also includes a graphical object 2516 defined by vertex data.

In some embodiments, the operating system 2520 is Microsoft Windows ® operating system, proprietary UNIX-like operating system, or open source UNIX-like operating system from Microsoft corporation (using a variation of the Linux kernel). When Direct3DAPI is in use, the operating system 2520 uses a front-end shader compiler 2524 to compile any shader instructions 2512 that employ HLSL into a lower-order shader language. The compilation may be a just-in-time (JIT) compilation or the application may execute a shader precompilation. In some embodiments, during compilation of 3D graphics application 2510, the high-order shaders are compiled into low-order shaders.

In some embodiments, the user-mode graphics driver 2526 includes a back-end shader compiler 2527 for converting shader instructions 2512 into a hardware-specific representation. When the OpenGL API is in use, shader instructions 2512 in the GLSL high-level language are passed to user-mode graphics driver 2526 for compilation. In some embodiments, the user mode graphics driver 2526 uses the operating system kernel mode functions 2528 to communicate with the kernel mode graphics driver 2529. In some embodiments, the kernel mode graphics driver 2529 communicates with the graphics processor 2532 to dispatch commands and instructions.

IP check cash

One or more aspects of at least one embodiment may be implemented by representative code stored on a machine-readable medium that represents and/or defines logic within an integrated circuit such as a processor. For example, a machine-readable medium may include instructions representing various logic within a processor. When read by a machine, the instructions may cause the machine to fabricate logic to perform the techniques described herein. Such representations (referred to as "IP cores") are reusable units of logic for an integrated circuit that may be stored on tangible, machine-readable media as hardware models that describe the structure of the integrated circuit. The hardware model may be supplied to various customers or manufacturing facilities that load the hardware model on the manufacturing machines that manufacture the integrated circuits. An integrated circuit may be fabricated such that the circuit performs the operations described in association with any of the embodiments described herein.

Fig. 26 is a block diagram illustrating an IP core development system 2600 that may be used to fabricate integrated circuits to perform operations, according to an embodiment. IP core development system 2600 can be used to generate a modular, reusable design that can be incorporated into a larger design or used to build an entire integrated circuit (e.g., an SOC integrated circuit). Design facility 2630 may generate software simulations 2610 of IP core designs using a high-level programming language (e.g., C/C + +). Software simulation 2610 may be used to design, test, and verify the behavior of an IP core. A Register Transfer Level (RTL) design may then be created or synthesized in accordance with simulation model 2600. RTL design 2615 is a decimation (iteration) of the behavior of an integrated circuit that models the flow of digital signals between hardware registers, including associated logic that is executed using the modeled digital signals. In addition to the RTL design 2615, lower level designs at the logic level or transistor level may also be created, designed, or synthesized. Thus, the specific details of the initial design and simulation may vary.

The RTL design 2615 or equivalent may be further synthesized by the design facility into a hardware model 2620, which may employ a Hardware Description Language (HDL) or some other representation of physical design data. The HDL may be further simulated or tested to verify the IP core design. Non-volatile memory 2640 (e.g., a hard disk, flash memory, or any non-volatile storage medium) may be used to store the IP core design for delivery to the 3 rd party manufacturing facility 2665. Alternatively, the IP core design may be communicated (e.g., via the internet) over a wired connection 2650 or a wireless connection 2660. Manufacturing facility 2665 may then fabricate integrated circuits based at least in part on the IP core design. The integrated circuit being fabricated may be configured to perform operations in accordance with at least one embodiment described herein.

Fig. 27 is a block diagram illustrating an example system on chip integrated circuit 2700 that may be fabricated using one or more IP cores, according to an embodiment. The exemplary integrated circuit includes one or more application processors 2705 (e.g., CPUs), at least one graphics processor 2710, and may additionally include an image processor 2715 and/or a video processor 2720, any of which may be a modular IP core from the same or multiple different design facilities. The integrated circuit includes peripheral or bus logic including USB controller 2725, UART controller 2730, SPI/SDIO controller 2735, I²S/I²C controller 2740. Additionally, the integrated circuit may include a display device 2745 coupled to one or more of a High Definition Multimedia Interface (HDMI) controller 2750 and a Mobile Industry Processor Interface (MIPI) display interface 2755. Storage may be provided by flash memory subsystem 2760 (including flash memory and flash memory controller). A memory interface may be provided via the memory controller 2765 for accessing SDRAM or SRAM memory devices. Some integrated circuits additionally include an embedded security engine 2770.

Additionally, other logic and circuitry may be included in the processor of integrated circuit 2700 including additional graphics processors/cores, peripheral interface controllers, or general purpose processor cores.

The invention provides a group of technical schemes, which are as follows:

1. an electronic processing system, comprising:

an application processor;

a persistent storage medium communicatively coupled to the application processor; and

a graphics subsystem communicatively coupled to the application processor, wherein the graphics subsystem includes:

a first graphics engine to process a graphics workload; and

a second graphics engine to offload at least a portion of the graphics workload from the first graphics engine.

2. The system of claim 1, wherein the second graphics engine comprises:

a low precision computing engine.

3. The system of claim 1, further comprising:

a wearable device for housing the second graphics engine.

4. A graphics device, comprising:

a first graphics engine to process a graphics workload; and

5. The apparatus of claim 4, wherein the second graphics engine comprises:

a low precision computing engine.

6. The apparatus of claim 5, wherein the low precision computing engine is to perform at least one of temporal warping, spatial warping, and machine learning.

7. The apparatus of claim 6, further comprising:

a second context for the second graphics engine that is independent of the first context for the first graphics engine.

8. The apparatus of claim 4, further comprising:

a wearable device for housing the second graphics engine.

9. The apparatus of claim 8, wherein the second graphics engine is further to offload rendering work from the first graphics engine.

10. The apparatus of claim 10, wherein the wearable display comprises a head-mounted display, and wherein the second graphics engine is further to offload foveated rendering work from the first graphics engine.

11. A method of processing a graphics workload, comprising:

processing a graphics workload with a first graphics engine; and

offloading at least a portion of the graphics workload from the first graphics engine to a second graphics engine.

12. The method of claim 11, further comprising:

providing a low precision computing engine for the second graphics engine.

13. The method of claim 12, further comprising:

performing at least one of time warping, spatial warping, and machine learning with the low-precision computing engine.

14. The method of claim 13, further comprising:

providing a second context for the second graphics engine that is independent of the first context for the first graphics engine.

15. The method of claim 11, further comprising:

a wearable device is provided for housing the second graphics engine.

16. The method of claim 15, further comprising:

offloading rendering work from the first graphics engine to the second graphics engine.

17. The method of claim 16, further comprising:

providing a head mounted display for housing the second graphics engine; and

offloading a foveated rendering job from the first graphics engine to the second graphics engine.

18. At least one computer-readable medium comprising a set of instructions that, when executed by a computing device, cause the computing device to:

processing a graphics workload with a first graphics engine; and

19. The at least one computer-readable medium of claim 18, comprising a further set of instructions that, when executed by a computing device, cause the computing device to:

providing a low precision computing engine for the second graphics engine.

20. The at least one computer-readable medium of claim 19, comprising a further set of instructions that, when executed by a computing device, cause the computing device to:

21. The at least one computer-readable medium of claim 20, comprising a further set of instructions that, when executed by a computing device, cause the computing device to:

22. The at least one computer-readable medium of claim 18, comprising a further set of instructions that, when executed by a computing device, cause the computing device to:

a wearable device is provided for housing the second graphics engine.

23. The at least one computer-readable medium of claim 22, comprising a further set of instructions that, when executed by a computing device, cause the computing device to:

24. The at least one computer-readable medium of claim 23, comprising a further set of instructions that, when executed by a computing device, cause the computing device to:

providing a head mounted display for housing the second graphics engine; and

Advantageously, any of the above systems, processors, graphics processors, devices, and/or methods may be configured or integrated with (e.g., or portions thereof) any of the various embodiments described herein, including, for example, those described in the following additional notes and examples.

Additional notes and examples:

example 1 may include an electronic processing system comprising an application processor, a persistent storage medium communicatively coupled to the application processor, and a graphics subsystem communicatively coupled to the application processor, wherein the graphics subsystem includes a first graphics engine to process a graphics workload and a second graphics engine to offload at least a portion of the graphics workload from the first graphics engine.

Example 2 may include the system of example 1, wherein the second graphics engine comprises a low precision compute engine.

Example 3 may include the system of any of examples 1 to 2, further comprising: a wearable device equipped with the second graphics engine.

Example 4 may include a graphics device comprising a first graphics engine to process a graphics workload and a second graphics engine to offload at least a portion of the graphics workload from the first graphics engine.

Example 5 may include the apparatus of example 4, wherein the second graphics engine comprises a low precision computing engine.

Example 6 may include the apparatus of example 5, wherein the low-precision computing engine is to be used to perform at least one of time warping, spatial warping, and machine learning.

Example 7 may include the apparatus of example 6, further comprising: a second context for the second graphics engine that is independent of the first context for the first graphics engine.

Example 8 may include the apparatus of example 4, further comprising: a wearable device equipped with the second graphics engine.

Example 9 may include the apparatus of example 8, wherein the second graphics engine is further to be used to offload rendering work from the first graphics engine.

Example 10 may include the apparatus of example 10, wherein the wearable display comprises a head-mounted display, and wherein the second graphics engine is further to be used to offload foveated rendering work from the first graphics engine.

Example 11 may include a method of processing a graphics workload, the method comprising: processing a graphics workload with a first graphics engine; and offloading at least a portion of the graphics workload from the first graphics engine to the second graphics engine.

Example 12 may include the method of example 11, further comprising: providing a low precision computing engine for the second graphics engine.

Example 13 may include the method of example 12, further comprising: performing at least one of time warping, spatial warping, and machine learning with the low-precision computing engine.

Example 14 may include the method of example 13, further comprising: providing a second context for the second graphics engine that is independent of the first context for the first graphics engine.

Example 15 may include the method of example 11, further comprising: providing a wearable device equipped with the second graphics engine.

Example 16 may include the method of example 15, further comprising: offloading rendering work from the first graphics engine to the second graphics engine.

Example 17 may include the method of example 16, further comprising: a head mounted display is provided with a second graphics engine, and the foveated rendering job is offloaded from the first graphics engine to the second graphics engine.

Example 18 may include at least one computer-readable medium comprising a set of instructions that, when executed by a computing device, cause the computing device to: processing a graphics workload with a first graphics engine; and offloading at least a portion of the graphics workload from the first graphics engine to the second graphics engine.

Example 19 may include the at least one computer-readable medium of example 18, comprising a further set of instructions that, when executed by the computing device, cause the computing device to: providing a low precision computing engine for the second graphics engine.

Example 20 may include the at least one computer-readable medium of example 19, comprising a further set of instructions that, when executed by the computing device, cause the computing device to: performing at least one of time warping, spatial warping, and machine learning with the low-precision computing engine.

Example 21 may include the at least one computer-readable medium of example 20, comprising a further set of instructions that, when executed by the computing device, cause the computing device to: providing a second context for the second graphics engine that is independent of the first context for the first graphics engine.

Example 22 may include the at least one computer-readable medium of example 18, comprising a further set of instructions that, when executed by the computing device, cause the computing device to: providing a wearable device equipped with the second graphics engine.

Example 23 may include the at least one computer-readable medium of example 22, comprising a further set of instructions that, when executed by the computing device, cause the computing device to: offloading rendering work from the first graphics engine to the second graphics engine.

Example 24 may include the at least one computer-readable medium of example 23, comprising a further set of instructions that, when executed by the computing device, cause the computing device to: a head mounted display is provided with a second graphics engine, and the foveated rendering job is offloaded from the first graphics engine to the second graphics engine.

Example 25 may include a graphics device, the device comprising: means for processing a graphics workload with a first graphics engine; and means for offloading at least a portion of the graphics workload from the first graphics engine to the second graphics engine.

Example 26 may include the apparatus of example 25, further comprising means for providing a low precision computing engine for the second graphics engine.

Example 27 may include the apparatus of example 26, further comprising: means for performing at least one of time warping, spatial warping, and machine learning with the low-precision computing engine.

Example 28 may include the apparatus of example 27, further comprising: means for providing a second context for the second graphics engine that is independent of the first context for the first graphics engine.

Example 29 may include the apparatus of example 25, further comprising: means for providing a wearable device incorporating the second graphics engine.

Example 30 may include the apparatus of example 29, further comprising: means for offloading rendering work from the first graphics engine to the second graphics engine.

Example 31 may include the apparatus of example 30, further comprising: means for providing a head mounted display housing a second graphics engine; and means for offloading the foveated rendering work from the first graphics engine to the second graphics engine.

Embodiments may be adapted for use with all types of semiconductor integrated circuit ("IC") chips. Examples of such IC chips include, but are not limited to, processors, controllers, chipset components, Programmable Logic Arrays (PLAs), memory chips, network chips, system on chip (SoC), SSD/NAND controller ASICs, and the like. Furthermore, in some of the figures, signal conductors are represented by lines. Some may be different to indicate more constituent signal paths, have numerical labels to indicate several constituent signal paths, and/or have arrows at one or more ends to indicate primary information flow direction. However, this should not be construed in a limiting manner. Rather, such added detail may be used in conjunction with one or more exemplary embodiments to facilitate easier understanding of a circuit. Any represented signal lines, whether or not having additional information, may actually comprise one or more signals that may travel in multiple directions and may be implemented with any suitable type of signal scheme, such as digital or analog lines implemented with differential pairs, fiber optic lines, and/or single-ended lines.

Example sizes/models/values/ranges may have been given, even though the embodiments are not limited to the same. As manufacturing techniques (e.g., photolithography) mature over time, it is expected that devices of smaller size could be manufactured. Furthermore, well known power/ground connections to IC chips and other components may or may not be shown within the figures for simplicity of illustration and discussion, and so as not to obscure certain aspects of the embodiments. Additionally, arrangements may be shown in block diagram form in order to avoid obscuring the embodiments, and also in view of the fact that specifics with respect to implementation of such block diagram arrangements are highly dependent upon the platform within which the embodiments are to be implemented, i.e., such specifics should be well within purview of one skilled in the art. Where specific details (e.g., circuits) are set forth in order to describe example embodiments, it should be apparent to one skilled in the art that the embodiments can be practiced without, or with variation of, these specific details. The description is thus to be regarded as illustrative instead of limiting.

The term "coupled" may be used herein to refer to any type of relationship (direct or indirect) between the components in question, and may apply to electrical, mechanical, fluid, optical, electromagnetic, electromechanical or other connections. Moreover, the terms "first," "second," and the like may be used herein only to facilitate discussion, and do not convey importance to a particular temporal or chronological order, unless otherwise indicated. Additionally, it is understood that the indefinite article "a" or "an" conveys the meaning of "one or more" or "at least one".

As used in this application and in the claims, a list of items linked by one or more of the terms "may mean any combination of the listed items. For example, the phrase "A, B or one or more of C" may mean a; b; c; a and B; a and C; b and C; or A, B and C.

Embodiments have been described above with reference to specific embodiments. However, those skilled in the art will understand that various modifications and changes may be made thereto without departing from the broader spirit and scope of embodiments as set forth in the appended claims. The foregoing description and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Claims

1. A first graphics processing unit for processing a graphics workload, comprising:

circuitry implemented at least in part in one or more of configurable logic or fixed functionality logic hardware, the circuitry to process the graphics workload, wherein to process the graphics workload, the circuitry is to:

rendering information is obtained from the second graphics processing unit,

receiving gaze tracking data, an

Generating a frame based on the gaze tracking data and by one or more of a time warping operation based on the rendering information received from the second graphics processing unit or a spatial warping operation based on the rendering information received from the second graphics processing unit, wherein the time warping operation is a re-projection operation and the spatial warping operation is a frame rate up-conversion operation.

2. The first graphics processing unit of claim 1, wherein to process the graphics workload, the circuitry is to perform a denoising operation.

3. The first graphics processing unit of claim 1, wherein the first graphics processing unit is attached to a head mounted display.

4. The first graphics processing unit of claim 1, wherein the first graphics processing unit has less processing power than the second graphics processing unit.

5. The first graphics processing unit of claim 1, wherein the first graphics processing unit is to perform a distortion operation of the graphics workload based on tracked head activity.

6. The first graphics processing unit of claim 1, wherein the rendering information comprises lighting information.

7. A Head Mounted Display (HMD), comprising:

a display for presenting a frame;

a wireless module to communicate with a second graphics processing unit;

one or more cameras or tracking modules for detecting gaze tracking data; and

a first graphics processing unit to process a graphics workload, wherein to process the graphics workload, the first graphics processing unit is to:

obtaining rendering information from the second graphics processing unit,

receiving the gaze tracking data, an

Generating the frame based on the gaze tracking data and by one or more of a time warping operation based on the rendering information received from the second graphics processing unit or a spatial warping operation based on the rendering information received from the second graphics processing unit, wherein the time warping operation is a re-projection operation and the spatial warping operation is a frame rate up-conversion operation.

8. The HMD of claim 7, wherein to process the graphics workload, the first graphics processing unit is to perform a denoising operation.

9. The HMD of claim 7, wherein the first graphics processing unit has less processing power than the second graphics processing unit.

10. The HMD of claim 7, wherein the first graphics processing unit is to perform a distortion operation of the graphics workload based on tracked head activity.

11. The HMD of claim 7, wherein the rendering information comprises lighting information.

12. At least one non-transitory computer-readable storage medium comprising a set of instructions that, when executed by a computing device, cause the computing device to:

processing a graphics workload, wherein to process the graphics workload, the computing device is to:

obtaining rendering information from a second graphics processing unit with a first graphics processing unit,

receiving gaze tracking data with the first graphics processing unit, an

Generating, with the first graphics processing unit, a frame based on the gaze tracking data and by one or more of a time warping operation based on the rendering information received from the second graphics processing unit or a spatial warping operation based on the rendering information received from the second graphics processing unit, wherein the time warping operation is a re-projection operation and the spatial warping operation is a frame rate up-conversion operation.

13. The at least one non-transitory computer-readable storage medium of claim 12, comprising a further set of instructions that, when executed by the computing device, cause the computing device to:

performing a denoising operation with the first graphics processing unit to process the graphics workload.

14. The at least one non-transitory computer-readable storage medium of claim 12, wherein the first graphics processing unit is attached to a head-mounted display.

15. The at least one non-transitory computer-readable storage medium of claim 12, wherein the first graphics processing unit has less processing power than the second graphics processing unit.

16. The at least one non-transitory computer-readable storage medium of claim 12, comprising a further set of instructions that, when executed by the computing device, cause the computing device to:

performing, with the first graphics processing unit, a distortion operation of the graphics workload based on the tracked head activity.

17. The at least one non-transitory computer-readable storage medium of claim 12, wherein the rendering information comprises lighting information.

18. A first graphics processing unit for processing a graphics workload, comprising:

means for obtaining rendering information from a second graphics processing unit,

means for receiving gaze tracking data, and

means for generating a frame based on the gaze tracking data and by one or more of a time warping operation based on the rendering information received from the second graphics processing unit or a spatial warping operation based on the rendering information received from the second graphics processing unit, wherein the time warping operation is a re-projection operation and the spatial warping operation is a frame rate up-conversion operation.

19. The first graphics processing unit of claim 18, further comprising means for performing a denoising operation of the graphics workload.

20. The first graphics processing unit of claim 18, wherein the first graphics processing unit is attached to a head mounted display.

21. The first graphics processing unit of claim 18, wherein the first graphics processing unit has less processing power than the second graphics processing unit.

22. The first graphics processing unit of claim 18, further comprising means for performing a distortion operation of the graphics workload based on tracked head activity.

23. The first graphics processing unit of claim 18, wherein the rendering information comprises lighting information.

24. A method for processing a graphics workload by a first graphics processing unit, comprising:

rendering information is obtained from the second graphics processing unit,

receiving gaze tracking data, an

25. The method of claim 24, further comprising performing a denoising operation of the graphics workload.

26. The method of claim 24, wherein the first graphics processing unit is attached to a head mounted display.

27. The method of claim 24, wherein the first graphics processing unit has less processing power than the second graphics processing unit.

28. The method of claim 24, further comprising performing a distortion operation of the graphics workload based on tracked head activity.

29. The method of claim 24, wherein the rendering information comprises lighting information.

30. A first graphics processing unit for processing a graphics workload, comprising:

processing the graphics workload, the first graphics processing unit to:

generating rendering information; and

communicating the rendering information to a second graphics processing unit,

wherein the first graphics processing unit is to make a frame generation operation of the graphics workload available to the second graphics processing unit to generate a frame based on gaze tracking data and by one or more of a time warping operation based on the rendering information received from the second graphics processing unit or a spatial warping operation based on the rendering information received from the second graphics processing unit, wherein the time warping operation is a re-projection operation and the spatial warping operation is a frame rate up-conversion operation.

31. At least one non-transitory computer-readable storage medium comprising a set of instructions that, when executed by a computing device, cause the computing device to:

generating rendering information using a first graphics processing unit, an

Communicating the rendering information to a second graphics processing unit with the first graphics processing unit,

32. A first graphics processing unit for processing a graphics workload, comprising:

means for generating rendering information, and

means for communicating the rendering information to a second graphics processing unit,

33. A method for processing a graphics workload by a first graphics processing unit, comprising:

generating rendering information, an

Communicating the rendering information to a second graphics processing unit,

34. A system for processing a graphics workload, comprising:

a first graphics processing unit, the first graphics processing unit comprising:

processing the graphics workload, the first graphics processing unit to:

generating rendering information; and

communicating the rendering information to a second graphics processing unit,

wherein the first graphics processing unit is to make a frame generation operation of the graphics workload available to the second graphics processing unit to generate a frame based on gaze tracking data and by one or more of a time warping operation based on the rendering information received from the second graphics processing unit or a spatial warping operation based on the rendering information received from the second graphics processing unit, wherein the time warping operation is a re-projection operation and the spatial warping operation is a frame rate up-conversion operation;

a second graphics processing unit, the second graphics processing unit comprising:

rendering information is obtained from a first graphics processing unit,

receiving gaze tracking data, an

Generating a frame based on the gaze tracking data and by one or more of a time warping operation based on the rendering information received from the first graphics processing unit or a spatial warping operation based on the rendering information received from the first graphics processing unit, wherein the time warping operation is a re-projection operation and the spatial warping operation is a frame rate up-conversion operation.

35. The system of claim 34, wherein to process the graphics workload, the circuitry is to perform a denoising operation.

36. The system of claim 34, wherein the second graphics processing unit is attached to a head mounted display.

37. The system of claim 34, wherein the second graphics processing unit has less processing power than the first graphics processing unit.

38. The system of claim 34, wherein the second graphics processing unit is to perform a distortion operation of the graphics workload based on tracked head activity.

39. The system of claim 34, wherein the rendering information comprises lighting information.